Showing 1–50 of 2,137 results for author: Yu, S

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Authors: Bo Liu, Simon Yu, Yiding Jiang, Ao Qu, Andrew Zhao, Zichen Liu, Junsu Kim, Zijian Zhou, Seungone Kim, Tongzheng Ren, Mickel Liu, Hanfei Yu, Zhaorun Chen, Weiyan Shi, Paul Pu Liang, Luke Zettlemoyer, Yejin Choi, Natasha Jaques

Abstract: Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM… ▽ More Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that learns to act in them. Each is a stateful, multi-turn environment (state transitions, reward functions, and verification code), so one interface spans reasoning problems and multi-step agentic tool use. The Reasoning Agent's regret is estimated using the gap between its reward with and without privileged hints; in optimizing this regret signal the Environment Designer learns to target environments at the edge of the agent's capabilities while keeping them feasible. Through extensive experimentation, we find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory. Scaling to 30B-parameter models, SPADE improves over the strongest fixed-environment baseline by +5.3 on average across eight held-out math, science, code, and reasoning benchmarks, and lifts the tool-use setting by +5.7 on BFCL-v4 multi-turn and +13.9 on ACEBench-Agent; on the games setting, the margin over the strongest baseline grows with model scale. By making environment design itself a learnable component, SPADE takes a concrete step toward open-ended self-improvement. △ Less

Submitted 19 August, 2026; originally announced August 2026.

Comments: Work in progress. Project page: https://spade-rl.github.io ; Code: https://github.com/spade-rl/spade

SeisEvo: Evolution of Seismic Data Reconstruction Algorithms by Agents

Authors: Yingjie Xu, Siwei Yu, Jianwei Ma

Abstract: Classical seismic data reconstruction relies on manually designed structural priors and iterative operators, whose coupled design space is far larger than manual trial and error can explore systematically. Deep-learning methods encode the reconstruction rules in learned weights rather than in an explicit operator that can be inspected and modified. We propose SeisEvo (Seismic Algorithm Evolution),… ▽ More Classical seismic data reconstruction relies on manually designed structural priors and iterative operators, whose coupled design space is far larger than manual trial and error can explore systematically. Deep-learning methods encode the reconstruction rules in learned weights rather than in an explicit operator that can be inspected and modified. We propose SeisEvo (Seismic Algorithm Evolution), which does not optimize a single reconstruction result but searches for the algorithm that produces it. Starting from a classical reconstruction algorithm, an LLM-driven multi-agent search modifies only the components that the user has opened for editing, without prescribing the mechanism to be discovered. Candidates that violate the physical constraints of the task are rejected outright, and the remaining ones are scored by execution. The output is neither an agent system nor a neural network, but a standalone white-box algorithm that requires no agent or neural network at inference time. For interpolation without added noise, the search discovered a residual-gated, phase-aligned dip-consistency projection; Evo-POCS improves the SNR over classic POCS by 3.49 dB on average across missing ratios from 30% to 70%. For simultaneous interpolation and denoising, it discovered a reliability-grouped singular-value shrinkage; Evo-MSSA improves the average reconstruction SNR by more than 7 dB over classic MSSA and by more than 3 dB over a stronger rank-reduction baseline. Both operators retain their gains on data not used during the search. To the best of our knowledge, this is the first study to formulate the design of a seismic reconstruction operator as a constrained, LLM-driven program evolution task. Agentic algorithm evolution can thus complement deep learning in discovering explicit, inspectable, and deployable seismic processing algorithms. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Large Language Models in Mental Health: A Systematic Review of Applications, Innovations, and Ethical Challenges

Authors: Yisong Chen, Yifan Gao, Sijing Yu, Chuqing Zhao, Yang Lu

Abstract: We present a review on the applications of large language models (LLMs) in health, e.g., social media analysis, clinical conversational agents, therapy support tools, prompt engineering, multimodal learning, and ethical considerations. We integrate findings from interdisciplinary studies utilizing diverse data sources such as social media posts, electronic medical records, and multimodal inputs to… ▽ More We present a review on the applications of large language models (LLMs) in health, e.g., social media analysis, clinical conversational agents, therapy support tools, prompt engineering, multimodal learning, and ethical considerations. We integrate findings from interdisciplinary studies utilizing diverse data sources such as social media posts, electronic medical records, and multimodal inputs to enable early detection of depression, suicide risk assessment, personalized therapy support, and psychoeducational content generation. Our review highlights advancements in LLM models and annotation strategies that enhance interpretability and clinical relevance, while we also emphasize the critical role of prompt engineering for domain adaptation. We also discuss emerging multimodal fusion techniques integrating text, speech, and sensor data for improved mental health diagnosis and monitoring. Finally, we address ongoing ethical, sociotechnical, and regulatory challenges, and advocate frameworks to ensure safe, equitable, and accountable deployment of LLMs in real-world mental health care. △ Less

Submitted 30 May, 2026; originally announced August 2026.

Comments: Systematic review. Published in Journal of Industrial Integration and Management (2025). Applications of large language models in mental health, including social media analysis, clinical conversational agents, therapy support tools, multimodal learning, and ethical considerations

Journal ref: Journal of Industrial Integration and Management (JIIM), 2025

LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localization

Authors: Wen Li, Shangshu Yu, Dunqiang Liu, Qiming Xia, Sheng Ao, Siqi Shen, Chenglu Wen, Cheng Wang

Abstract: Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can take days, limiting practical deployment. Recent works improve training efficiency by decoupling SCR into a scene-agnostic backbone and scene-specific prediction heads, where the backbone is pretrained on source datasets and frozen for new scenes, an… ▽ More Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can take days, limiting practical deployment. Recent works improve training efficiency by decoupling SCR into a scene-agnostic backbone and scene-specific prediction heads, where the backbone is pretrained on source datasets and frozen for new scenes, and only lightweight heads are optimized. However, we find that this paradigm heavily depends on the pretrained backbone. Existing decoupled methods can match conventional SCR methods fully optimized for each new scene when LiDAR configurations are similar to those used during backbone pretraining, but their accuracy drops noticeably on datasets collected with different LiDAR sensors. This suggests that efficient LiDAR localization requires representations that capture stable scene geometry across LiDAR configurations. Motivated by this observation, we propose LightLoc++, a sensor-robust and efficient outdoor LiDAR localization framework. To support sensor-robust representation learning, we introduce SULID, a synchronized urban multi-LiDAR dataset with representative 32-, 64-, and 128-beam rotating LiDARs, extensive cross-sensor overlap, and diverse urban scenes. Using SULID, we pretrain a sensor-robust backbone through cross-sensor consistency learning. LightLoc++ further preserves efficient new-scene learning by incorporating sample classification guidance and redundant sample downsampling, which reduce regression ambiguity and computational redundancy in large-scale outdoor scenes. Extensive experiments on multiple outdoor LiDAR localization benchmarks demonstrate that LightLoc++ achieves state-of-the-art localization performance with the lowest new-scene training cost among compared methods. Code and dataset will be made available at https://github.com/liw95/LightLoc-PlusPlus. △ Less

Submitted 15 August, 2026; originally announced August 2026.

Comments: 19 pages, 10 figures

SAEFUZZ: Smart Contract Vulnerability Detection through Statically Guided Evolutionary Fuzzing

Authors: Shiting Yu, Rundong Wei, Xiaoqi Li

Abstract: The effectiveness of smart contract fuzzing depends strongly on whether generated transactions reach deep, state-dependent execution paths. Existing fuzzers often generate highly random call sequences, wasting executions on semantically invalid or low-value states and leaving vulnerabilities that require specific invocation orders unexplored. We present a lightweight method for generating fuzz tes… ▽ More The effectiveness of smart contract fuzzing depends strongly on whether generated transactions reach deep, state-dependent execution paths. Existing fuzzers often generate highly random call sequences, wasting executions on semantically invalid or low-value states and leaving vulnerabilities that require specific invocation orders unexplored. We present a lightweight method for generating fuzz test cases under bytecode-level static guidance. We construct an Ethereum virtual machine control-flow graph, extract paths containing vulnerability-relevant instructions, recover function selectors, and order externally callable functions according to storage read-write dependencies. A coverage-guided evolutionary strategy then generates, evaluates, recombines, and mutates executable seeds. Five dedicated runtime oracles target reentrancy, integer overflow or underflow, block-state dependence, unsafe delegate calls, and frozen Ether. The evaluation uses deployed Ethereum contracts, including labelled vulnerable contracts. SAEFUZZ detects most labelled vulnerable contracts, yielding 98.50% accuracy, 90.00% precision, and 81.82% recall. It also achieves 84.07% mean instruction coverage, with valid test cases accounting for 93.48% of generated cases. Ablation results indicate that static guidance, directed seed generation, and vulnerability-specific oracles each contribute to the final performance. △ Less

Submitted 15 August, 2026; originally announced August 2026.

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

Authors: Wei-Chieh Huang, Weizhi Zhang, Yuchen Wu, Yankai Chen, Eric Hanchen Jiang, Wooseong Yang, Yiwei Yang, Henry Peng Zou, Hanrong Zhang, Ying Nian Wu, Haolun Wu, Kai-Wei Chang, Philip S. Yu, Xue Liu, Aylin Caliskan

Abstract: Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely the underlying medium in which memory is represented and stored, should be used under different operating regimes. We present a controlled harness evaluation of memory substrates for memory-augmented agents, covering dense and sparse indices, text re… ▽ More Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely the underlying medium in which memory is represented and stored, should be used under different operating regimes. We present a controlled harness evaluation of memory substrates for memory-augmented agents, covering dense and sparse indices, text records, structural stores, hierarchical stores, refinement-based memories, parametric updates, and activation-compatible context mechanisms. Across three backbone models and four benchmark suites spanning user-centric question answering and agent-centric decision-making, we instrument 26 performance and efficiency metrics under a unified harness. Our results show that no single substrate consistently dominates: broad retrieval benefits long-context factual QA, while excessive retrieval can harm sequential decision-making by shifting attention away from action-critical context. Scalability introduces a further routing axis, as substrates that perform well at moderate history lengths can become costly or brittle at longer horizons. These findings motivate substrate routing as a necessary component of adaptive agent memory systems and provide empirical guidance for designing efficient, reliable, and regime-aware long-term memory for LLM agents. Code will be made available upon acceptance. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models

Authors: Haoran Wang, Xiongxiao Xu, Philip S. Yu, Kai Shu

Abstract: Large language models (LLMs) and large vision-language models (LVLMs) have demonstrated impressive generative capabilities, yet ensuring their outputs align with user intent is still challenging. While most existing approaches address this issue at the training stage, inference-time approaches like decoding methods offer a more efficient and scalable solution. Decoding methods control model genera… ▽ More Large language models (LLMs) and large vision-language models (LVLMs) have demonstrated impressive generative capabilities, yet ensuring their outputs align with user intent is still challenging. While most existing approaches address this issue at the training stage, inference-time approaches like decoding methods offer a more efficient and scalable solution. Decoding methods control model generation by guiding token-level selection, performing sequence-level generation, or generating tokens in parallel to accelerate the process. In this survey, we identify three emerging paradigms from recent works on decoding methods for LLMs and LVLMs, provide a systematic review of these methods, highlight ongoing challenges, and discuss potential future research directions. Our goal is to underscore the efficiency and effectiveness of decoding methods and offer a practical view of their applications. Paper lists and more resources on decoding methods for LLMs and LVLMs can be found at https://github.com/wang2226/Awesome-LLM-Decoding. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: ACM SIGKDD Explorations Newsletter, Volume 28, Issue 1

BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials

Authors: An Vuong, Chen Zhao, Jin Hu, Shui-Qing Yu, Xintao Wu

Abstract: Stacked bilayer materials exhibit rich stacking-dependent properties driven by the interplay between strong intra-layer bonding and weak inter-layer van der Waals interactions. The computational discovery of such materials is challenging because accurate structure generation typically relies on expensive DFT-based optimization, while existing machine-learning models often fail to explicitly distin… ▽ More Stacked bilayer materials exhibit rich stacking-dependent properties driven by the interplay between strong intra-layer bonding and weak inter-layer van der Waals interactions. The computational discovery of such materials is challenging because accurate structure generation typically relies on expensive DFT-based optimization, while existing machine-learning models often fail to explicitly distinguish different interaction types during property prediction. To address these challenges, we propose a machine-learning framework for efficient construction and property prediction of stacked bilayer materials. The framework employs a MatterSim-D3-based structural optimization workflow to generate DFT-quality bilayer structures from monolayer building blocks and stacking configurations at substantially reduced computational cost. For property prediction, we introduce BDIP-Net (Bilayer Dual-Interaction Potential Network), a graph neural network that explicitly models intra-layer and inter-layer interactions through interaction-specific potential representations and adaptive message fusion. We evaluate the proposed framework on BiDB, HetDB, and SAMBA, encompassing homobilayers, heterobilayers, and twisted bilayer systems. Results show that the MatterSim-D3-based workflow closely reproduces DFT-PBE-D3 optimized structures, while BDIP-Net consistently outperforms existing graph neural network and potential-based approaches for bilayer property prediction. △ Less

Submitted 28 July, 2026; originally announced August 2026.

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

Authors: Kai Chen, Jifeng Ding, Ning Ding, Jiaye Ge, Lixin Gu, Yicheng Gu, Qipeng Guo, Ermo Hua, Haian Huang, Haozheng Hou, Jie Hou, Xiangyu Hong, Che Jiang, Minxi Jin, Cheng Liang, Dahua Lin, Dawei Liu, Kuikun Liu, Chengqi Lv, Haijun Lv, Han Lv, Ningsheng Ma, Biqing Qi, Jianmin Qian, Shiya Su , et al. (22 additional authors not shown)

Abstract: We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning. Using hidden states as cache and carrier, reasoners repeatedly query memory for required knowledge-vectors, while the knowledge is transmitted back to reasoning operators. Through this knowledge-reas… ▽ More We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning. Using hidden states as cache and carrier, reasoners repeatedly query memory for required knowledge-vectors, while the knowledge is transmitted back to reasoning operators. Through this knowledge-reasoning-separation architecture, Mobius achieves better knowledge compression and reasoning efficiency. Built upon Mobius-v0 architecture: 1) Our 7B model trained-from-scratch achieves similar downstream score as a 7B Transformer baseline with 62.6% of baseline's training data. 2) Our Intern-S2-Mobius, continually-pretrained from Qwen3.5-35B, achieves similar downstream score while delivering nearly 4x end-to-end inference speedup. △ Less

Submitted 14 August, 2026; originally announced August 2026.

HiCo-GS: Hierarchical Context Aggregation and Geometric Consistency for Octree Gaussian Splatting

Authors: Wei Zhang, Shengkai Yu, Shiqiang Gong, Qi Zhang, Qiang Li, Qi Wang

Abstract: Octree-based anchor Gaussian Splatting has emerged as a scalable representation for city-scale novel view synthesis, where multi-level anchors adaptively capture scene content from coarse building structures to fine architectural details. However, we identify a fundamental limitation in existing methods: cross-level feature isolation, where each level's anchor features are optimized independently… ▽ More Octree-based anchor Gaussian Splatting has emerged as a scalable representation for city-scale novel view synthesis, where multi-level anchors adaptively capture scene content from coarse building structures to fine architectural details. However, we identify a fundamental limitation in existing methods: cross-level feature isolation, where each level's anchor features are optimized independently with no inter-level communication, causing color drift on building facades and over-smoothing in textured regions. We present HiCo-GS, a high-fidelity reconstruction framework with two complementary modules. Cross-Level Context Aggregation (CLCA) enables bidirectional hierarchical prior injection by leveraging the octree's spatial containment structure to aggregate per-level context vectors into parent-self-child triplets, fused via a lightweight MLP with residual connection. Coarse-level structural priors flow down to inform fine-level anchors, while fine-level detail statistics feed back to prevent over-smoothing, at negligible computational overhead. Depth-Normal Geometric Consistency (DNGC) regularization enforces agreement between rendered normals and depth-derived normals through an alpha-weighted consistency loss, complemented by edge-aware smoothness losses with progressive warmup that exploit the strong planar priors ubiquitous in urban geometry to suppress floating artifacts. We further introduce the China-Pagoda dataset comprising 8 ancient Chinese pagodas with over 1,200 images each, featuring dense ornamental carvings, curved multi-layer eaves, and repetitive fine-grained textures. Extensive experiments on Mill19, UrbanScene3D, MatrixCity, and China-Pagoda demonstrate that HiCo-GS achieves state-of-the-art rendering quality and substantially cleaner geometry across real-world and synthetic urban benchmarks.Code: https://github.com/WZ-CS/HiCo-GS. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: 21 pages, including supplementary material. To appear in the Proceedings of the 34th ACM International Conference on Multimedia (MM '26)

HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geoscience

Authors: Ziqi Song, Zongyuan Xiang, James G. Ogg, Bruce S. Lieberman, Gabi Ogg, Natalia López Carranza, Wen Du, Yufei Ye, Shuan Li, Zhong Peng, Shaoqi Yu, Juye Wei, Ying Zhou, Jieping Ye, Jiang Yang

Abstract: Authoritative scientific knowledge in geoscience remains largely trapped in legacy monographs and historical literature, where unstructured text and complex layouts hinder computational access. We introduce HERMES, a scalable multi-agent framework that extracts structured data from ultra-long scientific documents. Using a coordinating large language model, HERMES integrates domain constraints, val… ▽ More Authoritative scientific knowledge in geoscience remains largely trapped in legacy monographs and historical literature, where unstructured text and complex layouts hinder computational access. We introduce HERMES, a scalable multi-agent framework that extracts structured data from ultra-long scientific documents. Using a coordinating large language model, HERMES integrates domain constraints, validation rules and evidence tracing within a unified document-level extraction process that incorporates parsed text, tables, figures and captions. Applied to the 55-volume Treatise on Invertebrate Paleontology, the system produced a structured database of 32,277 fossil taxonomic entities and 451,878 attributes, released online at https://treatise.geolex.org. Extraction performance remained stable across fossil groups (average F1 scores of approximately 0.90 for entities and 0.91 for attributes), improving per-volume efficiency approximately sixfold relative to the tested fully manual baseline. Evaluation in palaeomagnetism and geochemistry, conducted without additional model training, demonstrated transfer across distinct geoscience domains. This work provides a practical pathway to transform historical scientific literature into FAIR-oriented structured data, offering a sustainable infrastructure for data-intensive disciplines and large-scale knowledge integration. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: 31-page main manuscript with 6 figures and 3 tables; supplementary information included

ACM Class: I.2.7

MARCH: Scaling Recurrent Memory with Content-Routed State Anchors

Authors: Ming Zhang, Kaisen Yang, Shu Yu, Ermo Hua, Ning Ding, Xia Hu, Bowen Zhou, Chaochao Lu, Youbang Sun

Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic computation complexity during training and a key--value cache that grows linearly during autoregressive inference. Recurrent alternatives offer efficient decoding by compressing the entire history into a fixed-size state, but… ▽ More Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic computation complexity during training and a key--value cache that grows linearly during autoregressive inference. Recurrent alternatives offer efficient decoding by compressing the entire history into a fixed-size state, but often underperform on recall-intensive tasks since earlier associations usually get overwritten by subsequent updates, and only the most recent contextual information is retained. In this paper, we introduce Memory-Anchor Routing across Context History (MARCH), a network architecture that effectively scales state-space models beyond a fixed-size dimension, while maintaining computational efficiency over long-sequences. MARCH periodically caches cumulative recurrent-state checkpoints as state anchors and associates each anchor with a compact, content-conditioned anchor key. This lets MARCH maintain a memory bank, which can grow as context length increases, providing a controllable trade-off between historical resolution and memory cost. At each token, MARCH produces an anchor query to attend all causally available state anchors, and the output is calculated as an attention-style aggregation over all historical anchors along the current state. We show that after standard pretraining, MARCH consistently outperforms multiple linear attention variants across commonsense reasoning, LongBench, and in-context retrieval. These results demonstrate that content-routed state caching substantially strengthens recurrent long-range memory while preserving its native computation path. △ Less

Submitted 12 August, 2026; originally announced August 2026.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

Authors: Simon Yu, Nicholas Tomlin, Marwa Abdulhai, Ximing Lu, Derek Chong, Abe Hou, Dilara Soylu, Sergey Levine, Christopher D. Manning, Weiyan Shi

Abstract: Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against it overfits to narrow strategies that exploit the simulator's dominant mode, and… ▽ More Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against it overfits to narrow strategies that exploit the simulator's dominant mode, and such a policy transfers poorly to unseen simulators and real users. We formalize this collapse theoretically and propose two complementary solutions, one at inference time and one at training time. The inference-time solution, Verbalized Sampling, broadens the simulator's behavior by sampling from a verbalized response distribution, reducing mode collapse. The training-time solution, Co-Training, jointly optimizes the policy against a population of trainable simulators, preventing it from overfitting to any single simulator's mode. We validate both solutions on three multi-turn benchmarks: Persuasion for Good, $τ^2$-bench, and CooperBench. Verbalized Sampling improves held-out success by up to 9% over single-simulator RL, and Co-Training pushes gains further to 14%; the human study shows similar gain on real users. Both solutions preserve the policy diversity that collapses under single-simulator RL. To support further work in this direction, we release SCOPE, an open-source framework for Population Co-Training multi-agent RL. More broadly, our results suggest that the diversity of the training environment, not only the policy, is critical to the generalization of multi-turn RL to real-world deployment. △ Less

Submitted 17 August, 2026; v1 submitted 12 August, 2026; originally announced August 2026.

Comments: 42 pages, 29 figures

XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

Authors: Wooseong Yang, Wei-Chieh Huang, Weizhi Zhang, Yu Wang, Philip S. Yu, Junhyun Lee

Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns. Yet existing communication protocols either operate through text, discarding the sender's internal representations, or require architectural homogeneity for latent-level transfer. We identify the entity grounding problem in… ▽ More Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns. Yet existing communication protocols either operate through text, discarding the sender's internal representations, or require architectural homogeneity for latent-level transfer. We identify the entity grounding problem in cross-architecture communication: cross-attention bridges that transfer continuous representations across different LLM families suffer from rare-token compression collapse, where entity identity is lost in the continuous bottleneck (bridge-only F1 ~30%). We propose XBRIDGE, a decode-free communication protocol that addresses this through two mechanisms. Lexical Anchor Mapping (LAM) maps the sender's original context tokens to the receiver's vocabulary, providing discrete entity anchors. A Latent Enrichment Bridge (LEB) lets the receiver query the sender's hidden states for contextual enrichment. The entity anchors ground the bridge's contextual signals to specific entities through the receiver's own self-attention. Across three model families (Llama, Qwen, and Mistral), seven benchmarks, and both communication directions, XBRIDGE outperforms text-based communication on all seven tasks for each model pair while achieving 11x lower latency, and in a same-architecture setting it also exceeds a KV-sharing baseline on six of seven tasks. LEB requires only 264M trainable parameters (3.8% of the receiver), is trained on a small balanced sample set, and adds negligible inference overhead. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Comments: 18 pages, 4 figures

AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search

Authors: Weicheng Ye, Youran Sun, Xingyu Ren, Shunyao Yu, Chugang Yi, Haizhao Yang

Abstract: Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that searches over frozen research artifacts---hypotheses, executable expressions, platform evidence, rationales, and review status---rather than formulas… ▽ More Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that searches over frozen research artifacts---hypotheses, executable expressions, platform evidence, rationales, and review status---rather than formulas alone. To our knowledge, AgonAlpha is the first alpha-mining system to combine verified artifact search, a fresh-context adversarial reviewer with re-execution and veto authority, and pending-aware parallel budget allocation, together with a complete public evidence trail. Independent deployments on WorldQuant BRAIN produced SPECTACULAR-grade alphas across five users and six model backends, with Fitness reaching 9.50 and Sharpe reaching 3.48, while retaining prompt-to-expression provenance for every submission. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Software Engineering for and with GUI Agent

Authors: Shengcheng Yu, Yuchen Ling, Junyang Xing, Quan Zhou, Chunrong Fang, Zhenyu Chen

Abstract: GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications. However, this growth has outpaced the maturity of the field. GUI agents remain technically brittle, incompletely engineered, and insufficiently validated for sustained real-world use. They are evolving into closed-loop software systems. Within these systems, model reasoning is coupled with inter… ▽ More GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications. However, this growth has outpaced the maturity of the field. GUI agents remain technically brittle, incompletely engineered, and insufficiently validated for sustained real-world use. They are evolving into closed-loop software systems. Within these systems, model reasoning is coupled with interface perception, execution feedback, recovery, and human oversight. This evolution calls for a software engineering perspective that remains largely absent from existing research. We address this gap by reviewing 336 GUI-agent papers from January 2018 to April 2026. Five research questions examine the research landscape, architectures, evaluation, software lifecycle concerns, and future opportunities. Our findings show that the field has expanded sharply since 2024, while mobile and web settings remain dominant. Architectures increasingly adopt modular perceive-reason-act loops, but recovery, human escalation, safety enforcement, and auditability remain underdeveloped. This architectural imbalance extends to evaluation. Evaluations are becoming more interactive, but they remain centered on task success and are difficult to compare across protocols. More broadly, existing studies provide limited support for testing beyond benchmarks and for maintaining agents after release. Observability, privacy engineering, and systematic human oversight are also underdeveloped. Together, these findings show that capability improvements alone cannot ensure deployment readiness. Future research should connect dependable execution with lifecycle-centered testing and reproducible evaluation. It should also integrate permission and privacy controls with cost-aware, human-centered governance. This integration is necessary to build dependable, maintainable, secure, and deployable GUI-agent systems. △ Less

Submitted 10 August, 2026; originally announced August 2026.

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding

Authors: Xichen Zhang, Guankai Li, Yinghao Zhu, Shijian Wang, Sitong Wu, Shaozuo Yu, Meng Chu, Yuan Lu, Jiaya Jia

Abstract: Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-scale memory. However, current evaluations predominantly rely on brief clips and multiple-choice formats. This design allows minimal baselines that process only the last four frames to match or surpass complex streaming models, while answer options… ▽ More Deploying autonomous multimodal agents in continuous, real-world environments requires them to ingest unbounded audio-visual streams and maintain hour-scale memory. However, current evaluations predominantly rely on brief clips and multiple-choice formats. This design allows minimal baselines that process only the last four frames to match or surpass complex streaming models, while answer options also expose language shortcuts. We introduce StreamArena, a benchmark for hour-scale, interactive streaming video understanding. StreamArena contains 243 full-length videos averaging 88.8 minutes and 3,646 rigorously annotated, open-ended question-answer pairs that evaluate real-time perception, historical retrospection, proactive interaction, and multimodal tool utilization. Evaluation across diverse systems exposes a tension between continuous interaction and long-horizon multimodal comprehension. Methods that retain only recent frames cannot recover distant events, methods that convert past observations into text lose visual evidence, and methods that repeatedly compress visual memory struggle to preserve fine-grained details over time. We address this tension with StreamMind, a two-tier architecture that assigns latency-critical interaction and proactive monitoring to independently scheduled frontend workers, while backend workers asynchronously construct persistent multimodal memory and perform historical recall and external search. StreamMind outperforms existing streaming baselines across all four capabilities and reduces query-to-answer latency by reusing persistent state. △ Less

Submitted 6 August, 2026; originally announced August 2026.

When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters

Authors: Fangxin Wang, Ziyi Zhang, Diyi Zhuang, Langzhou He, Shiyu Wang, Baichuan Mo, Philip S. Yu

Abstract: Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discovery: mining interpretable features of a frozen forecaster's residual to drive a lightweight post-hoc corrector. Prior automated feature engineering models the data-generating process; corrective features instead model the model-failure process. We… ▽ More Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discovery: mining interpretable features of a frozen forecaster's residual to drive a lightweight post-hoc corrector. Prior automated feature engineering models the data-generating process; corrective features instead model the model-failure process. We present CRAFTER (Corrective Residual Agent with Feature-based Temporal Exploration and Reasoning), which keeps the backbone frozen and mines its residual with two complementary generators: a compositional search over the raw input channels, and a large language model (LLM) that proposes named feature combinations, binary flags, and short executable code. A single validation-grounded gate accepts or rejects every candidate regardless of its origin, and a validation-selected corrector applies the accepted features or leaves the forecast unchanged. This source-agnostic pipeline also allows prior feature-engineering systems to be evaluated under identical conditions, making CRAFTER an instrument for attributing forecast improvements to the feature source alone. Across six public datasets and six frozen backbones, CRAFTER surpasses every dedicated feature-engineering system at every feature budget, roughly doubling the improvement achieved by the corrector alone and reducing the error of the weakest backbones by up to 27%. These gains are robust across different LLM backends and persist even when applied on top of fine-tuned backbones. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Comments: 23 pages, 14 tables, 4 figures

LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching

Authors: Siwei Yu, Han Guo, Zhenwei Shi, Zhengxia Zou

Abstract: Dense image matching establishes pixel-wise correspondences and underpins broad applications in computer vision and photogrammetry. However, extending dense matching to global-scale remote sensing remains challenging because image pairs may differ in acquisition time, season, viewpoint, spatial resolution, and land-cover state. The resulting large geometric offsets, partial overlap, and intrinsica… ▽ More Dense image matching establishes pixel-wise correspondences and underpins broad applications in computer vision and photogrammetry. However, extending dense matching to global-scale remote sensing remains challenging because image pairs may differ in acquisition time, season, viewpoint, spatial resolution, and land-cover state. The resulting large geometric offsets, partial overlap, and intrinsically unmatchable regions make direct dense correspondence prediction unreliable and inefficient. We thus reformulate dense matching as localization-and-registration: first localizing the matchable overlap and affine geometry, then refining dense residuals within the aligned frame. Based on this formulation, we propose LoRetta, a foundation model coupling matchability-aware affine localization with guided dense registration. We also introduce LEVIR-GM, a global-scale multi-temporal optical matching benchmark with dataset-native matchability labels (103K aligned, 827K augmented pairs, six continents, five years, 0.5-1024 m resolution). We further establish a unified evaluation protocol for sparse, semi-dense, and dense matchers. On LEVIR-GM, LoRetta achieves an area under the curve (AUC) of 83.3%, outperforming the strongest baseline RoMa v2 by 1.6 points, with larger percentage of correct keypoints (PCK) gains of 6.5 and 8.2 points at 1 and 2 pixels, while reducing inference latency by 47.8%. Astronaut-to-satellite and unmanned aerial vehicle (UAV)-to-satellite geolocalization experiments further demonstrate its transferability as a reusable geometric aligner. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Comments: 17 pages, 12 figures, 6 tables. Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence. Project page: https://siweiyu.com/work/loretta/

Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning

Authors: Fangxu Yu, Tao Feng, Dehai Min, Zinan Lin, Weijia Xu, Michael Xu, Philip S. Yu, Ge Liu, Tianyi Zhou

Abstract: Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning, yet existing reward designs are complementary in their limitations: outcome-based rewards supervise only the final answer and let the model reach it without attending to the audio, whereas process-based rewards score the reasoning itself but rely o… ▽ More Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning, yet existing reward designs are complementary in their limitations: outcome-based rewards supervise only the final answer and let the model reach it without attending to the audio, whereas process-based rewards score the reasoning itself but rely on coarse, hand-crafted, and fixed criteria that neither adapt to each question nor stay grounded in the acoustic evidence. Moreover, questions differ in what they demand, with some hinging on perception and others on multi-step reasoning, and any static criterion weakens as the policy improves. Supervising the reasoning process with fine-grained, audio-grounded, and adaptive rewards is therefore crucial, yet challenging since such rewards are impractical to design by hand for every sample. To this end, we introduce AudioRubrics, a reinforcement learning framework that supervises audio reasoning with self-evolving, audio-grounded rubric rewards. AudioRubrics synthesizes per-sample rubrics from the raw waveform and, conditioned on the model's own rollouts, regenerates and reweights criteria per group, supplying a continuous learning signal that keeps targeting the current policy's weaknesses as static criteria saturate. Comprehensive evaluations across three audio reasoning benchmarks reveal that AudioRubrics substantially outperforms a wide range of open-source and training-based baselines. Furthermore, our analysis shows that the gains scale with the capability of the rubric generator and judge, and AudioRubrics converges to a stable reasoning length that avoids both degenerate collapse and unbounded growth. The improvement in audio perception further demonstrates the effectiveness of anchoring supervision in the acoustic evidence. Our project page is available at https://audiorubrics.github.io. △ Less

Submitted 3 August, 2026; originally announced August 2026.

Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce

Authors: Shicheng Fan, Mingdai Yang, Duohao Wang, Canyu Chen, Yongfeng Zhang, Hua Wei, Manling Li, Julian McAuley, Kun Zhang, Philip S. Yu, Kejing Yu, Zhiwei Liu

Abstract: In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in natural language and delegate the corresponding tasks to agents. Commerce, however, requires independently controlled Buyer and Merchant agents to interact in a shared market while preserving their private objectives an… ▽ More In vibe coding, people describe software in natural language and delegate implementation to AI agents. By analogy, vibe commerce allows people to express buying or selling goals in natural language and delegate the corresponding tasks to agents. Commerce, however, requires independently controlled Buyer and Merchant agents to interact in a shared market while preserving their private objectives and distinct authority. We introduce Agentic Commerce World (ACWorld), an environment for evaluating such agents across ongoing transactions. Through its Vibe Commerce Protocol (VCP), ACWorld validates agent actions before updating shared transaction state and records the resulting interactions, making agent behavior auditable and evaluation reproducible. The ACWorld Benchmark contains a 200-task capability-coverage track and a 60-task large-catalog track that searches 785,022 transactable listings. Across ten models, mean scores range from 65.9% to 85.6% and from 56.1% to 91.4%, respectively. Our analysis shows that process-level evidence is necessary: final state alone can miss evaluated errors, incomplete trajectories still retain useful process signals, and large-catalog tasks expose bottlenecks across stages. △ Less

Submitted 3 August, 2026; originally announced August 2026.

How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories

Authors: Hui Wei, Junda Wu, Sheldon Yu, Sizhe Zhou, Yizhu Jiao, Ming Zhong, Bowen Jin, Tong Yu, Shijia Pan, Jiawei Han, Julian McAuley

Abstract: Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on output-level signals or collapse processing depth into a single trajectory-level scalar, leaving step-wise effort opaque. We propose Step-Aware Reasoning Energy (SARE), a geometric framework that quantifies effort at the g… ▽ More Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on output-level signals or collapse processing depth into a single trajectory-level scalar, leaving step-wise effort opaque. We propose Step-Aware Reasoning Energy (SARE), a geometric framework that quantifies effort at the granularity of individual CoT steps via Centered Kernel Alignment (CKA) between Gram matrices of token hidden states across adjacent transformer layers, capturing inter-token relational structure without requiring eigenvector alignment or cluster correspondence. SARE further contextualizes this energy within reasoning's semantic progression by modeling CoT trajectories as transitions among latent semantic states. Across six reasoning benchmarks and three open-weight LLMs, we find that reasoning energy is highly non-uniform across step types, exhibiting phase-like transitions invisible to trajectory-level metrics; incorrect trajectories show systematically lower energy at critical reasoning junctions; and SARE-based features match or outperform output-based confidence baselines in most settings, indicating that internal geometric dynamics encode predictive information beyond surface-level signals. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: 13 pages, 3 figures

Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents

Authors: Mingdai Yang, Shicheng Fan, Kejing Yu, Duohao Wang, Li Sun, Hao Peng, Philip S. Yu, Zhiwei Liu

Abstract: LLM agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instructions to be honest, they fabricate attributes in a majority of listings across models. A platform's obvious remedy---verifying each claim against the truth---is unavailable, because it observes only a noisy, biased comp… ▽ More LLM agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instructions to be honest, they fabricate attributes in a majority of listings across models. A platform's obvious remedy---verifying each claim against the truth---is unavailable, because it observes only a noisy, biased complaint signal, never the ground truth. We design CARP, a reputation-penalty mechanism with a deadband that forgives complaint noise and a state-dependent severity that counters reputation-driven detection erosion. CARP requires no product-level ground truth and is robust to strategic gaming. CARP protects consumers by suppressing the sales volume of low-rated liars while sparing honest sellers. Paired with SPARC, it closes most of the consumer-welfare gap relative to a perfect-information oracle, without ever accessing the truth. It also achieves the best welfare of the policies we compare. We further show that this felt penalty becomes behaviorally binding through SPARC, a byte-clean code-gated reflection mechanism: LLM merchants fabricate when lying is free but restrain themselves when fabrication costs them sales, a self-interested response rather than compliance. We trace this distinction to penalty-gated self-correction reasoning, and observe the binding across models, with supporting confidence intervals. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Comments: 11 pages

Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation

Authors: Long Zhang, Hao Jiang, Sheng Yu, Fei Pan, Peng Jiang, Kun Gai

Abstract: While large language models (LLMs) have advanced ID-based recommendation through Semantic ID (SID) modeling, existing SID generation frameworks largely follow a single-representation-then-quantization paradigm. This design faces two bottlenecks: semantic entanglement mixes heterogeneous attributes, such as geography, brand, and category, causing information loss during quantization, low-quality SI… ▽ More While large language models (LLMs) have advanced ID-based recommendation through Semantic ID (SID) modeling, existing SID generation frameworks largely follow a single-representation-then-quantization paradigm. This design faces two bottlenecks: semantic entanglement mixes heterogeneous attributes, such as geography, brand, and category, causing information loss during quantization, low-quality SIDs, and severe collisions; moreover, black-box representation learning provides neither explicit attribute semantics nor clear geographic or semantic meanings for SID positions. These limitations weaken both retrieval reliability and the ability to diagnose or control SID generation. We propose Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation (LGRID). LGRID introduces a generative disentanglement paradigm through an Encode -> Disentangle -> Align -> Quantize pipeline. It first uses joint LLM encoding to preserve cross-attribute geographic-semantic dependencies, rather than encoding fields independently. A Structured Disentangled Block then routes hidden states into attribute-aligned slots for geographic and semantic factors. Synergistic Alignment Learning makes these slots both generatively decodable and discriminative for retrieval, while Dual-Stream Residual Quantization separately discretizes the two streams into compact SIDs with explicit attribute correspondence. This design yields interpretable SIDs with positions grounded in item attributes and local-service semantics. Experiments on Kuaishou and Foursquare show that LGRID consistently outperforms strong SID baselines, achieving up to a 5.44 percent relative AUC gain. It also achieves over 99 percent attribute-decoding accuracy for coarse geographic fields and reduces the full-SID collision rate to 39.9 percent, compared with 97.0 percent for LGSID. △ Less

Submitted 30 July, 2026; originally announced July 2026.

LimICE: Integrating LLM into ICE Framework for Efficient Loop Invariant Inference

Authors: Kai Fan, ShiWen Yu, GuangSheng Fan, HaoAng Chi, WanWei Liu, Ji Wang

Abstract: Loop invariant synthesis is a fundamental problem in program verification, yet the inherent undecidability makes it highly challenging. Recent studies have increasingly employed various machine learning techniques to generate loop invariants. However, most of these methods adopt a monolithic approach. Due to the inability to strictly constrain the learning process, learning-based methods struggle… ▽ More Loop invariant synthesis is a fundamental problem in program verification, yet the inherent undecidability makes it highly challenging. Recent studies have increasingly employed various machine learning techniques to generate loop invariants. However, most of these methods adopt a monolithic approach. Due to the inability to strictly constrain the learning process, learning-based methods struggle to simultaneously consider all necessary conditions and generate complete invariants when tackling complex problems. In fact, a loop invariant is often an ordered sequence of lemmas, rather than a single invariant formula. This motivates us to propose Incremental ICE, a novel learning framework for incremental synthesis. Our framework integrates the incremental philosophy of IC3 into the general invariant learning framework ICE. By defining a lemma-specific learning objective and introducing a counterexample filtering mechanism, we can achieve sound incremental learning. Under this framework, we instantiate a loop invariant synthesis tool, LimICE, which leverages LLMs to generate the ordered sequence of lemmas and incorporates ICE-DT as a fallback mechanism to complement the lemma sequence. Experiments on 367 linear benchmarks and 50 nonlinear benchmarks demonstrate the effectiveness of the proposed approach. LimICE solves 349 (out of 367) linear problems on an average of 15.2 seconds and 47 (out of 50) nonlinear problems on an average of 8.8 seconds. Compared to the state-of-the-art LLM-based baseline, our approach solves 12-24% more instances while running 36-63% faster across linear and nonlinear benchmarks. LimICE also consistently outperforms strong non-LLM baselines and solves at least 86 and 27 additional instances on the linear and nonlinear benchmarks, respectively. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Comments: 21 pages, 2 figures

AgentS4D: Benchmarking Runtime Risks across the Execution Lifecycle of LLM-Based Workspace Agents

Authors: Jiajun Zhou, Zhaoxuan Ke, Jihang Ye, Xuanze Chen, Shanqing Yu, Qi Xuan

Abstract: Large language model (LLM)-based workspace agents execute stateful, multi-step workflows across heterogeneous resources, external tools, and persistent state. Their safety must therefore be assessed from actions, side effects, and state changes throughout execution. Although recent benchmarks have advanced executable safety testing and trajectory-aware verification, they rarely provide a unified a… ▽ More Large language model (LLM)-based workspace agents execute stateful, multi-step workflows across heterogeneous resources, external tools, and persistent state. Their safety must therefore be assessed from actions, side effects, and state changes throughout execution. Although recent benchmarks have advanced executable safety testing and trajectory-aware verification, they rarely provide a unified account of where risks enter, how they elicit unsafe behavior, which harms they target, and where supporting evidence appears during execution. We introduce AgentS4D, a sandboxed benchmark for lifecycle-wide runtime safety evaluation. Its four-dimensional runtime-safety framework uses six risk-entry sources, six induction strategies, and nine target harms to guide case construction, while seven lifecycle checkpoints organize post-run evidence. AgentS4D contains 328 risk-injected cases. We evaluate all 20 combinations of four harnesses (Hermes, OpenClaw, Claude Code, and Codex) and five LLM backends (GPT-5.5, Gemini 3.1 Pro, DeepSeek-V4-Pro, MiniMax-M3, and Qwen3.7-Plus) on these cases, yielding 6,560 runs. Overall, 4,461 runs (68.0%) trigger prespecified unsafe signals. Across the 20 configurations, the observed safety of an agent system varies with both its harness-LLM pairing and how risk is introduced. Agent systems exhibit markedly different safety behavior when the same induction strategy reaches them through different risk carriers. They also respond differently to the same target harm when it is realized through different carriers and strategies. Moreover, 4,344 runs (66.22% overall) are unsafe yet complete. Thus, task completion cannot establish runtime safety, and testing only one form of a risk can conceal important weaknesses. Evaluations should examine complete agent configurations across diverse risk conditions and retain evidence throughout execution. △ Less

Submitted 29 July, 2026; originally announced July 2026.

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Authors: Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou, Shanqing Yu, Qi Xuan

Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasingly examine agent memory security, yet few trace the same malicious semantics across persistence, downst… ▽ More Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasingly examine agent memory security, yet few trace the same malicious semantics across persistence, downstream consequences, and selective repair under diverse memory-backend comparisons. To address this gap, we introduce MemSecBench, a task-grounded benchmark for the lifecycle security of agent memory systems. It contains 310 cases drawn from 48 realistic contexts across code and science, daily life, and office work. Each case follows a controlled Write--Execute--Forget protocol in an isolated runtime under an exact agent configuration, defined by an agent harness, a memory backend, and an LLM backend. Evidence-based adjudication combines a deterministic write check, checkpoint-specific judge-model evaluations, and programmatic gates across seven lifecycle checkpoints. The experimental design spans a 24-configuration matrix of two agent harnesses, four memory backends, and three LLM backends. Across all 24 configurations, malicious memory persists in 84.2% of all cases, and the full Write--Execute chain succeeds in 50.3%. Among successfully poisoned cases, 59.6% complete the full Execute chain, while 56.1% achieve selective repair.Compared with matched Native configurations, the largest absolute differences are 16.1 percentage points for end-to-end attack success and 41.3 percentage points for selective repair. These descriptive contrasts indicate that the evaluated memory system stacks differ in lifecycle security, both in the propagation of malicious memory and in selective repair after successful memory poisoning. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

Authors: Sizhe Zhou, Sheldon Yu, Hui Wei, Junda Wu, Siru Ouyang, Yizhu Jiao, Shijia Pan, Julian McAuley, Yu Zhang, Tong Yu, Jiawei Han

Abstract: Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools. Yet research has largely passed over this medium: prior systems design bespoke memory representations and study retrieval over them, leaving the default's two working assumptions untested: that an agent can… ▽ More Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools. Yet research has largely passed over this medium: prior systems design bespoke memory representations and study retrieval over them, leaving the default's two working assumptions untested: that an agent can keep a growing store organized as memories accumulate, conflict, and go stale, and that this organization pays. We present the first systematic exploration of filesystem-based memory for LLM agents. We formalize the setting as three roles around one memory filesystem: a management agent integrates and organizes incoming content, a search agent answers queries with cited sources, and an execution agent supplies task trajectories that are distilled into skills, unifying declarative memory and skills in a single store. Across long-conversation benchmarks and embodied tasks, we vary memory shape (agent-organized hierarchy, verbatim dump, chunk retrieval), stream scale, tool harness (sandboxed shell, memory-tool-style functions, varied search tooling), and the strengths of the management and search agents, tracking answer quality, cost, and store health as memory grows. What organization reliably buys is search economy: organized stores roughly halve retrieval cost where material is large. Today's agents, however, fall short of the default's promise: in our growth study, organization erodes for all but the strongest management agent, and no agent we measure converts organization itself into better answers. And the model is not the only lever over a store's shape: changing the tool set alone reshapes the store as strongly as swapping the model. The study turns the filesystem default from an assumption into a design space for agent memory. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Comments: 59 pages, 12 figures, 18 tables

WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models

Authors: Hao Jiang, Peiru Du, Pengfei Yao, Mengting Li, Siyuan Lou, Kuo Cai, Sheng Yu, Qiang Luo, Jian Liang, Ruiming Tang, Fei Pan, Peng Jiang, Wenwu Ou

Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs). Existing approaches typically enhance recommendation with explicit Chain-of-Thought (CoT) under the Think-then-Answer paradigm. However, generating lengthy rationales introduces substantial inference overhead, while fixed CoT templates st… ▽ More Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs). Existing approaches typically enhance recommendation with explicit Chain-of-Thought (CoT) under the Think-then-Answer paradigm. However, generating lengthy rationales introduces substantial inference overhead, while fixed CoT templates struggle to model diverse, dynamic, and context-dependent user interests. We propose WhisperRec, an efficient latent reasoning framework for FRMs. WhisperRec compresses teacher-generated CoT into learnable latent reasoning tokens, enabling a Latent-Reason-then-Answer paradigm that performs reasoning in latent space without producing verbose rationales. This design retains decision-relevant reasoning information while avoiding the latency bottleneck of autoregressive rationale generation. Specifically, it first introduces Multi-View Adaptive CoT (MV-ACoT) to construct diverse, high-quality supervision from complementary perspectives on user interests. MV-ACoT also adapts reasoning complexity to each instance, applying lightweight analysis to clear cases and targeted multi-factor reasoning to challenging ones. Building on a pre-trained FRM, WhisperRec then employs a three-stage Latent Reasoning Alignment procedure to progressively internalize teacher CoT into latent representations. Finally, curriculum-based post-training activates latent-token reasoning for downstream recommendation while preserving standard recommendation capability. Experiments on an industrial-scale Kuaishou dataset and the public Kuaishou LLM-Rec benchmark show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines. Compared with explicit CoT Think and No-Think variants, WhisperRec improves SID@64 by 17.44% and 9.33%, respectively, and achieves over 10x higher online inference throughput. △ Less

Submitted 30 July, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

LLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM Serving

Authors: Ming-Yen Lee, Hanchen Yang, Faaiq Waqar, Harsono Simka, Tushar Krishna, Muhammed Ahosan Ul Karim, Shimeng Yu

Abstract: The energy consumption of Large Language Model (LLM) serving is becoming a major system challenge as deployment scales, driven by hardware power and thermal constraints and rising electricity costs. A key contributor to chip energy dissipation is data movement between limited on-chip cache and off-chip High Bandwidth Memory (HBM). Meanwhile, emerging memory technologies such as monolithic 3D (M3D)… ▽ More The energy consumption of Large Language Model (LLM) serving is becoming a major system challenge as deployment scales, driven by hardware power and thermal constraints and rising electricity costs. A key contributor to chip energy dissipation is data movement between limited on-chip cache and off-chip High Bandwidth Memory (HBM). Meanwhile, emerging memory technologies such as monolithic 3D (M3D) integration of cache memories at the Back-End-Of-Line (BEOL) of logic chips enable larger and denser on-chip memories, creating new opportunities to reduce costly off-chip traffic. However, it remains unclear whether continuously scaling on-chip memory using emerging technologies can effectively improve the energy efficiency of LLM serving. To address this gap, we develop LLMET (LLM with Emerging Technology), a validated cross-layer simulation framework, and conduct a comprehensive study on the impact of large-capacity on-chip memory technologies across a broad range of models, applications and platforms. Utilizing M3D technology to expand the L2 cache from 40MB to 1GB yields a 44% reduction in chip energy during the Llama3.1-70B prefill phase with a 16K context window, based on LLMET simulation on a dual NVIDIA A100 GPU setup. On the 8x NVIDIA B200-like platform, extending the L2 cache from 128MB to 4GB saves the prefill energy by up to 24%. For the edge platform and workloads, the decode energy saving reaches 30% when increasing the 8MB cache size to 256MB. These results highlight the promise of ultra-large on-chip memories for energy-efficient LLM serving systems. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Comments: 6 pages

Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations

Authors: Seunghun Yu, Meiyi Zhu, Petar Popovski, Joonhyuk Kang, Osvaldo Simeone

Abstract: Detecting when the statistical behavior of an engineered system changes, and identifying which component is responsible, are core problems in the monitoring of telecommunication networks, robotic platforms, security infrastructure, and multi-agent systems. In safety- and mission-critical deployments, such decisions must be accompanied by statistical reliability guarantees rather than by point esti… ▽ More Detecting when the statistical behavior of an engineered system changes, and identifying which component is responsible, are core problems in the monitoring of telecommunication networks, robotic platforms, security infrastructure, and multi-agent systems. In safety- and mission-critical deployments, such decisions must be accompanied by statistical reliability guarantees rather than by point estimates alone. Conformal changepoint localization (CONCH) and conformal root cause analysis (CROC) meet this need by returning confidence sets that contain the true changepoint, or the true root-cause stream, with a user-specified probability, without parametric assumptions on the data-generating process. In practice, however, observations are frequently corrupted, e.g., by outliers, sensor faults, or adversarial perturbations. While the finite-sample coverage of these procedures is preserved under contamination, the resulting confidence sets can become uninformatively large. Adopting a Huber-type contamination model, this paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC), which downweight observations that are likely to be corrupted with the goal of reducing confidence set size when data may be corrupted. The weighting mechanism, derived from a formal bound on the unknown corrupted data densities, leverages pre-existing second-order classifier-based uncertainty signals, such as those produced by evidential deep learning or Bayesian learning. W-CONCH and W-CROC are further generalized by introducing a meta-learning procedure for the weights that optimizes a differentiable surrogate of the confidence set size. Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size while maintaining the target coverage. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Comments: 34 pages, 6 figures

Kimi K3: Open Frontier Intelligence

Authors: Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, M. C., Jianfeng Cai, Xinyuan Cai, Peizhou Cao, Yuxuan Cao, Ziwei Chai, Y. Charles, H. S. Che, Guanduo Chen, Guangyu Chen, Guanzheng Chen, Huarong Chen, Jia Chen, Jianlong Chen, Jun Chen, Kexin Chen, Peng Chen, Ruijue Chen, Wentao Chen, Xin Chen, Yang Chen , et al. (377 additional authors not shown)

Abstract: We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across sequence length and model depth. Together with Stable LatentMoE, which effectively activates 16 of 896 routed experts per token… ▽ More We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across sequence length and model depth. Together with Stable LatentMoE, which effectively activates 16 of 896 routed experts per token, and refined training and data recipes, these advances yield an approximately 2.5x improvement in overall scaling efficiency over Kimi K2. Post-training highlights reinforcement learning across general, agentic, and coding domains and multiple reasoning-effort levels, enabling compositional generalization and robust long-horizon execution. At 2.8T scale, Kimi K3 is supported by infrastructure advances in multiple areas: algorithm-system co-design for KDA, perfectly balanced expert-parallel training with efficient memory management, million-token agentic RL with persistent rollout and sandbox states, and deployment innovations. Extensive evaluations show that Kimi K3 achieves frontier-level performance across long-horizon coding, agentic, knowledge, reasoning, and vision tasks. While its overall performance still trails the most powerful proprietary models, namely Claude Fable 5 and GPT-5.6 Sol, Kimi K3 consistently outperforms other open and proprietary models evaluated in our suite. We release the full Kimi K3 model weights to facilitate future research and accelerate the broader deployment and adoption of frontier intelligence. △ Less

Submitted 7 August, 2026; v1 submitted 27 July, 2026; originally announced July 2026.

Comments: K3 tech report

IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data

Authors: Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira, Arturas Nakvosas, Hatef Otroshi Shahreza, Sébastien Marcel, Rishabh Shukla, Aditya Takkar, Rushil Khullar, Lalak Yadav, Gourav Gupta, Anant Gupta, Shiqi Yu, Vitomir Struc, Naser Damer, Fadi Boutros

Abstract: This paper presents a summary of the Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data (AFMFR), held at the 2026 International Joint Conference on Biometrics (IJCB 2026). The competition received a total of eight valid submissions from four distinct teams across two complementary tracks: a Full Data Track, in which participants adapt the CLIP ViT-L/14 fou… ▽ More This paper presents a summary of the Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data (AFMFR), held at the 2026 International Joint Conference on Biometrics (IJCB 2026). The competition received a total of eight valid submissions from four distinct teams across two complementary tracks: a Full Data Track, in which participants adapt the CLIP ViT-L/14 foundation model using large-scale synthetic identity data, and a Limited Data Track, designed to reflect more resource-constrained adaptation regimes. All training data was generated exclusively using IDPERTURB. Submitted solutions are ranked based on verification and identification performance across a diverse suite of benchmarks, including LFW, CFP-FP, AgeDB-30, CALFW, CPLFW, IJB-B, IJB-C, and TinyFace, using the Borda count method. Fairness evaluation is additionally conducted on the RFW dataset across four demographic groups. The results demonstrate that adaptation of the CLIP foundation model with synthetic training data substantially improves over the off-the-shelf model and, in several cases, surpasses the baseline. Notably, full fine-tuning with Sub-Center ArcFace (DMSTI-Neurotechnology) leads the Full Data Track, while rank-stabilized LoRA adaptation (Idiap-BSP) proves most effective under limited-data conditions. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Comments: Accepted at the IEEE International Joint Conference on Biometrics 2026 (IJCB 2026)

Neonatal Hypoxic-ischaemic Encephalopathy Classification from the EEG and HRV Signals Using a Conformer based Masked Autoencoder

Authors: Shuwen Yu, William P Marnane, Geraldine B. Boylan, Gordon Lightbody

Abstract: In this paper, we propose the MAEConformer, a novel self-supervised learning framework that combines the Conformer architecture with the Masked Autoencoder (MAE) paradigm for large-scale representation learning from unlabelled electroencephalography (EEG) and heart rate variability (HRV) signals. By integrating convolutional operations with Transformer-based self-attention, MAEConformer effectivel… ▽ More In this paper, we propose the MAEConformer, a novel self-supervised learning framework that combines the Conformer architecture with the Masked Autoencoder (MAE) paradigm for large-scale representation learning from unlabelled electroencephalography (EEG) and heart rate variability (HRV) signals. By integrating convolutional operations with Transformer-based self-attention, MAEConformer effectively captures both local temporal patterns and long-range contextual dependencies in physiological time series. To enhance reconstruction fidelity and representation quality, a multi-resolution short-time Fourier transform (MR-STFT) loss is incorporated alongside the reconstruction objective, enabling the model to jointly learn temporal and spectral characteristics across multiple scales. Modality-specific EEG and HRV MAEConformer models were pretrained on 6,030h and 4,868h of unlabelled recordings, respectively, and subsequently transferred to expert-annotated downstream tasks. Experimental results demonstrate that the learned representations provide strong transferability and data efficiency. In EEG-based hypoxic ischemic encephalopathy (HIE) severity classification, the pretrained MAE-EEG model achieved test AUCs of 97.19% and 96.56% for binary and four-class classification tasks, respectively, outperforming a range of state-of-the-art supervised and self-supervised baselines. On the HRV-based HIE severity classification task, MAE-HRV achieved a test AUC of 82.42%, surpassing both self-supervised Transformer-based and supervised convolutional baselines. These findings demonstrate the effectiveness of MAEConformer for learning robust and transferable representations across multiple physiological modalities. △ Less

Submitted 26 July, 2026; originally announced July 2026.

Comments: Paper submits to IEEE Transactions on Neural Networks and Learning Systems

PRISM: Polynomial Representations for Interaction-Structured Motor Control

Authors: Seung Hyun Lee, Stella X. Yu

Abstract: Robot policies are typically MLPs mapping observations to actions. Yet robot observations are physical variables, and many action-relevant cues arise not from individual variables but from their interactions; power, inertial effects, contact, slip, and compliance depend on products among observable signals. We introduce PRISM, a policy representation that makes polynomial interactions among observ… ▽ More Robot policies are typically MLPs mapping observations to actions. Yet robot observations are physical variables, and many action-relevant cues arise not from individual variables but from their interactions; power, inertial effects, contact, slip, and compliance depend on products among observable signals. We introduce PRISM, a policy representation that makes polynomial interactions among observable physical variables explicit, learnable, and compact. Rather than listing all polynomial terms, PRISM uses a factorized polynomial module to expose higher-order interaction features efficiently. In reinforcement learning, it keeps the standard MLP backbone but applies a gradually activated element-wise polynomial function after it. In imitation learning, it replaces linear proprioceptive conditioning in Diffusion Policy with a polynomial layer trained end-to-end. Across humanoid locomotion and contact-rich manipulation, PRISM improves performance over standard MLP policies and larger MLPs with matched capacity, showing that interaction structure cannot be replaced by capacity alone. It also yields sensorless compliant behavior without force, wrench, tactile input, contact labels, or admittance control. These results suggest that polynomial representations should become a standard architectural choice for embodied motor control. The project page is available at https://lsh3163.github.io/prism/ △ Less

Submitted 26 July, 2026; originally announced July 2026.

BioZKFHE: Scalable Encrypted Biometric Identification via Verifiable Homomorphic Similarity Evaluation

Authors: Rundong Xin, Taotao Wang, Xiaoxiao Wu, Weizhi Meng, Shengli Zhang, Shui Yu

Abstract: Large-scale biometric identification in outsourced settings requires two properties simultaneously: biometric templates and queries must remain protected during computation, and the encrypted similarity outputs produced by an untrusted compute node must be verifiably correct before any application result is released. Existing FHE-based biometric systems primarily address confidentiality, while pra… ▽ More Large-scale biometric identification in outsourced settings requires two properties simultaneously: biometric templates and queries must remain protected during computation, and the encrypted similarity outputs produced by an untrusted compute node must be verifiably correct before any application result is released. Existing FHE-based biometric systems primarily address confidentiality, while practical verifiability introduces two bottlenecks in the underlying encrypted 1:N matching layer: rotation- and bandwidth-heavy similarity evaluation and the high cost of proving repeated homomorphic similarity traces. We present BioZKFHE, a framework for scalable encrypted biometric identification via verifiable homomorphic similarity evaluation that combines BGV homomorphic computation with committee-mediated proof opening/decryption and smart-contract verification of opened proof batches. To reduce encrypted storage and avoid rotation-heavy encrypted 1:N matching, we propose Single-Coefficient Multi-Value (SCMV) packing, which binds multiple quantized embedding values into each plaintext entry through base-T expansion. To make proof generation practical, we propose Parallelizable and Verifiable Similarity Computation (PVSC), which exploits the Double-CRT execution structure of BGV to decompose each blockwise similarity trace into parallel proof instances that are opened and checked before result release. Under standard lattice assumptions and explicit committee/verifier assumptions, we analyze recoverability, noise growth, confidentiality, encrypted-output integrity, and finalized-result integrity. Experiments on FaceNet and MobileFaceNet show near-lossless biometric utility, up to 67 percent encrypted-storage reduction, and about 22 to 44 seconds end-to-end proof-verified runtime for 10k to 40k templates. △ Less

Submitted 24 July, 2026; originally announced July 2026.

Comments: Accepted for publication in IEEE Transactions on Dependable and Secure Computing. 28 pages, including supplementary material

Journal ref: IEEE Transactions on Dependable and Secure Computing, early access, 23 July 2026

Are Production Cloud Skills Adequately Tested? Measuring and Governing Skill Test Adequacy in Practice

Authors: Haotian Si, Junyi Chen, Shuyang Yu, Ruifeng Nie, Jiate Li, Jianqiang Zhao, Meng Li, Dengcheng He

Abstract: Cloud platforms increasingly deliver reusable Cloud Skills that guide AI agents through multi-step resource operations, user choices, validation, and recovery. Existing Skill evaluation primarily measures whether a Skill improves task success, but passing the available testcases does not reveal which behaviors specified by the Skill remain untested. We introduce Skill Test Adequacy, a scenario-con… ▽ More Cloud platforms increasingly deliver reusable Cloud Skills that guide AI agents through multi-step resource operations, user choices, validation, and recovery. Existing Skill evaluation primarily measures whether a Skill improves task success, but passing the available testcases does not reveal which behaviors specified by the Skill remain untested. We introduce Skill Test Adequacy, a scenario-conditioned criterion that evaluates a test suite against the complete set of operational test obligations specified by a Skill. Given a Skill package and normalized testcases containing a prompt, an initial resource state, and expected user decisions, the assessment determines whether each obligation is exercised by at least one testcase scenario; the resulting records provide both a suite-level score and explicit test gaps. We operationalize the criterion through parallel obligation proposals, disagreement-preserving aggregation, testcase-level status proposals, expert review, and source-grounded recommendations. Alibaba Cloud deploys this process as a mandatory gate before task-success evaluation and subsequent release checks. Among 157 initial assessments recorded before gate-driven remediation, 57 (36.3%) fall below the mandatory 80% gate and 76 (48.4%) remain below the recommended 90% level. The process also produces 132 reports containing 639 obligation-level recommendations, with a median of four per Skill. Finally, we release SkillAdeqBench, an exploratory subset of the reviewed records for studying automatic adequacy assessment. Skill Test Adequacy complements task-success evaluation by making the untested scope of production Cloud Skills explicit. △ Less

Submitted 11 August, 2026; v1 submitted 24 July, 2026; originally announced July 2026.

A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs

Authors: Bizu Feng, Zhimu Yang, Shuming Wang, Shaode Yu, Yuan Cheng, Xiaojun Qian, Zixin Hu

Abstract: We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradients provide an axiomatic formulation of attribution, but their practical use in deep GNNs typically relies on finite-sample numerical approximations to the path integral, requiring a trade-off between quadrature error and… ▽ More We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradients provide an axiomatic formulation of attribution, but their practical use in deep GNNs typically relies on finite-sample numerical approximations to the path integral, requiring a trade-off between quadrature error and computational cost. This paper proposes APEX, a model-attribution co-design framework that makes the attribution integral exactly computable under a polynomial GNN architecture. The key component is PolyGIN, a GIN-style graph network whose message-passing, normalization, and transformation operations preserve a bounded multivariate polynomial form for scalar model scores, such as pre-softmax logits. We show that, for a PolyGIN with $L$ polynomial transformation blocks, the derivative along the attribution path has degree at most $2^L-1$. Therefore, Gauss--Legendre quadrature can evaluate the Aumann--Shapley path integral exactly, up to floating-point precision, with $2^{L-1}$ deterministic evaluation points. The resulting attributions can be computed at the feature level and then aggregated into node-level scores while preserving completeness. Experiments on synthetic and real-world graph benchmarks show that PolyGIN maintains competitive predictive performance, while the complete APEX framework achieves higher attribution fidelity than the compared baselines and substantially reduces the number of evaluations required for path integration. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Comments: It has 23 pages

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs

Authors: Muyang Du, Shuang Yu, Junjie Lai

Abstract: Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2 is a state-of-the-art autoregressive TTS model consisting of a GPT, a flow-matching Diffusion Transformer, and a vocoder. Despite its high synthesis quality, its inference speed b… ▽ More Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2 is a state-of-the-art autoregressive TTS model consisting of a GPT, a flow-matching Diffusion Transformer, and a vocoder. Despite its high synthesis quality, its inference speed barely reaches real-time without streaming or batching support. We present Faster IndexTTS-2, which accelerates all neural network components of IndexTTS-2 for production deployment on GPUs using NVIDIA TensorRT and TensorRT-LLM. Faster IndexTTS-2 also enables streaming synthesis for latency-sensitive interactive applications, and batched inference across all components to maximize GPU utilization. Experiments on the Seed-TTS benchmark for both English and Chinese demonstrate up to 5.0$\times$ speedup on the autoregressive GPT and 3.6$\times$ end-to-end, with minimal degradation in word error rate, speaker similarity, and naturalness. Our methodology provides a practical reference for efficiently accelerating similar autoregressive speech models on GPUs. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Comments: 4 pages, 2 figures, 3 tables

Solar Open 2 Technical Report

Authors: Sungrae Park, Sanghoon Kim, Gyoungjin Gim, Jungho Cho, Hyunwoong Ko, Minbyul Jeong, Minjeong Kim, Keunwoo Choi, Chaehun Shin, Chanwoong Yoon, Dongjun Kim, Eunwon Kim, Gyungin Shin, Hyeonju Lee, Hyungkyu Kang, Inseo Song, Jisu Bae, Jiyoon Han, Jiyun Lee, Joonkee Kim, Junyeop Lee, Mikyoung Cha, Sangwon Yu, Sehwan Joo, Seokyoon Kang , et al. (28 additional authors not shown)

Abstract: We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks, scaled up from Solar Open 1 (Solar Open 100B). To hold entire agent trajectories in a single context, Solar Open 2 reaches a 1M-token window through a hybrid attention stack that interleaves one softmax layer among every three linear-attention layers, using no positional encoding and a gate… ▽ More We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks, scaled up from Solar Open 1 (Solar Open 100B). To hold entire agent trajectories in a single context, Solar Open 2 reaches a 1M-token window through a hybrid attention stack that interleaves one softmax layer among every three linear-attention layers, using no positional encoding and a gated delta rule extended to negative eigenvalues. To train at this scale under a fixed compute budget, we make training efficient in two ways: a stronger starting point, and higher-value data. For the starting point, we initialize Solar Open 2 from Solar Open 1, transferring the 5.69B-parameter shared skeleton that survives the architectural change and learning everything else through full pre-training. For the data, we curate for value per token: quality- and rarity-aware data curation and mixture-ratio optimization refine a 20T pool into a 10T mixture that, at equal token budget, outperforms the Solar Open 1 recipe. To build its agent skills, we train twelve domain specialists across purpose-built scenarios, then consolidate them into a single model by Multi-teacher On-Policy Distillation (MOPD). Against comparably sized open-weight models on English benchmarks, Solar Open 2 leads on MMLU-Pro, LiveCodeBench, and the APEX-Agents agentic suite, and stays competitive with the strongest (DeepSeek-V4-Flash and MiMo-V2.5) elsewhere. On Korean benchmarks, Solar Open 2 records the highest average of any model compared, including fast-tier closed APIs, and on Ko-GDPval, an in-house Korean officework-agent benchmark, it is competitive with DeepSeek-V4-Pro (1.6T) at less than a sixth of its size. △ Less

Submitted 23 July, 2026; v1 submitted 22 July, 2026; originally announced July 2026.

End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation

Authors: Jingzheng Li, Yufei Ge, Zhijun Chen, Qianren Mao, Zizhe Wang, Binhang Qi, Bing Li, Keyu Chen, Baochang Zhang, Xianglong Liu, Philip S Yu

Abstract: Generating closed-loop traffic scenarios that are both realistic and controllable is crucial for evaluating autonomous driving systems, especially under rare safety-critical interactions. Existing learning-based methods often struggle to balance controllability and realism, offering either limited fine-grained control over traffic behavior or controllable scenarios at the expense of behavioral pla… ▽ More Generating closed-loop traffic scenarios that are both realistic and controllable is crucial for evaluating autonomous driving systems, especially under rare safety-critical interactions. Existing learning-based methods often struggle to balance controllability and realism, offering either limited fine-grained control over traffic behavior or controllable scenarios at the expense of behavioral plausibility. This paper presents E2E-CDiff, an end-to-end conditional diffusion framework for controllable and realistic scenario generation. Conditioned on front-view visual observations, E2E-CDiff jointly denoises future motion states and executable low-level controls for route-interacting background vehicles. This unified state-action generation mitigates the planning-control mismatch in conventional two-stage trajectory-then-controller pipelines. Differentiable guidance further regulates speed, enforces drivable-area compliance, and supports collision-avoidance or collision-seeking behaviors, enabling both naturalistic and safety-critical scenario generation. Experiments on Bench2Drive show that E2E-CDiff achieves a favorable controllability-realism trade-off compared with representative reinforcement- and imitation-learning baselines, while its collision-guided variant induces challenging interactions across multiple autonomous driving systems. E2E-CDiff also performs competitively as a learning-based ego planner, demonstrating the generality of end-to-end state-action diffusion. △ Less

Submitted 20 July, 2026; originally announced July 2026.

RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts

Authors: Yuxin Xiong, Xunyi Jiang, Rohan Surana, Xintong Li, Sheldon Yu, Nikki Lijing Kuang, Ryan A. Rossi, Jingbo Shang, Tong Yu, Julian McAuley, Junda Wu

Abstract: Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals. However, extending group-relative optimization beyond verifiable settings is challenging because success in many tasks is not captured by a single correctness criterion. We propose… ▽ More Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals. However, extending group-relative optimization beyond verifiable settings is challenging because success in many tasks is not captured by a single correctness criterion. We propose \textbf{Reference-Relative Policy Optimization (RRPO)}, which generalizes GRPO by replacing direct correctness-based advantage construction with reference-relative contrastive comparisons. RRPO first uses \emph{stratified conditional rollouts} to construct positive and negative anchor sets, and then trains a metric projection head with a set-contrastive objective to compare candidate rollouts against these anchors. The resulting alignment scores directly define contrastive advantages: during policy optimization, the projection head is frozen, and the scores are centered within each rollout group in a standard group-relative objective. We evaluate RRPO using anchor-based contrastive advantages throughout policy optimization, without relying on task ground-truth verifiers. Across verifiable reasoning, open-ended generation, and post-SFT settings, RRPO remains competitive with verifier-based optimization, improves over weakly supervised baselines, and provides additional gains after supervised fine-tuning. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Operational Hallucination and Safety Drift in AI Agents

Authors: Shasha Yu, Fiona Carroll, Barry L. Bentley

Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms are relatively mature, extended interactions reveal structural vulnerabilities where initial alignment degrades over time. This paper empirically characterizes two observed failure modes across multiple state-of-the-art LL… ▽ More Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms are relatively mature, extended interactions reveal structural vulnerabilities where initial alignment degrades over time. This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift, the gradual erosion of declared safety intent leading to constraint-violating actions (e.g., textual refusal followed by reconnaissance and unsafe execution), and Operational Hallucination, persistent repetitive tool calls indicative of flawed state perception (e.g., livelocks even in legitimate tasks). Through controlled multi-turn evaluation on high-stakes ethical dilemmas, malicious requests, and benign controls, we quantify these phenomena using declaration-action gap and livelock metrics, demonstrating their cross-model prevalence under direct execution protocols. Root-cause analysis attributes the instabilities to the decoupling of reasoning context from execution state in current agent loops. We propose an Action-Aware Supervision Layer - a lightweight, plug-and-play architectural blueprint incorporating intent-action consistency checks, runtime state tracking, and forced termination primitives. Post-hoc simulation on captured failure trajectories shows the layer can intercept observed violations without false positives on benign cases. This work advances agent reliability by shifting focus from linguistic safeguards to enforceable architectural mechanisms for responsible agentic AI. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

Authors: Sheldon Yu, Tong Yu, Xunyi Jiang, Rohan Surana, Gagan Mundada, Sungchul Kim, Lina Yao, Julian McAuley, Junda Wu

Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shaping how a model reasons are prompt based approaches and operate at the input level, offering no fine-grained control over the reasoning process itself. Related work analyzes and discovers latent transition dynamics in th… ▽ More Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shaping how a model reasons are prompt based approaches and operate at the input level, offering no fine-grained control over the reasoning process itself. Related work analyzes and discovers latent transition dynamics in the reasoning traces from Large Language Models. Building on this, we statistically characterize these states, and show that failure trajectories get stuck in self-loops, exhausting the token budget without progress toward the final answer. To intervene on these failures, We propose SOPHIA: Steering Of reasoning Processes via Hidden-state Intervention and Activations. We treat each reasoning trace as a sequence of latent states rather than an unstructured texts, and investigate whether inference time interventions can provide fine-grained control over the self-looping reasoning process. We classify every prefix to a latent state, record step level transitions, and use them to construct a bank of steering vectors indexed by state pairs. At inference time, a controller infers the current state and, given a target state, retrieves the corresponding vector and can also detect self-loops online from the transition structure to prevent the model from sinking into a reasoning black hole. Through extensive experiments, our method reliably intervenes on self-loop failures, with steering vectors that generalize to different state pairs. End task accuracy and token efficiency indicate that fine-grained controllability results in better reasoning quality. △ Less

Submitted 20 July, 2026; originally announced July 2026.

An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

Authors: Zhida He, Xia Hu, Baichen Le, Chunxiao Li, Jiajia Li, Lijun Li, Chaochao Lu, Jing Shao, Youbang Sun, Hua Tang, Xiang Wang, Xiao Wang, Xiaoyu Wen, Tong Wu, Jia Xu, Peng Yu, Shu Yu, Jie Zhang, Qiaosheng Zhang, Yi Zhang, Xing-Ming Zhao, Tianhang Zheng, Ziyuan Zhou

Abstract: Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-la… ▽ More Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation. Within this framework, Intern-BioBreaker generates targeted jailbreak prompts to test whether aligned models can be induced to provide operational guidance for safety-sensitive biological tasks or produce sequence-level outputs with potentially harmful properties. Selected sequence outputs are then carried forward for DNA synthesis, host expression, and orthogonal protein verification to assess whether model-generated designs can yield the intended biological products. Our evaluation reveals a concerning gap between text-level safeguards and the risks posed by capable scientific models: (i) Intern-BioBreaker outperforms baseline attack models and reveals widespread bio-risk jailbreak vulnerabilities across both open-weight and proprietary frontier LLMs, with several targets reaching near-saturated or 100% task-level attack success rate (ASR); (ii) in sequence-level case studies, GPT-5.5 can be induced to generate modified viral candidate sequences with pathogenic potential; the corresponding translated proteins may exhibit even stronger receptor-binding affinity and thus enhanced infection potential; and (iii) end-to-end verification shows that selected model-generated biological designs are not merely textual artifacts, but can be physically realized under controlled experimental settings. These findings underscore the need for stronger biological red-teaming, nucleic acid synthesis screening, and safety mechanisms that keep pace with model capabilities. △ Less

Submitted 6 August, 2026; v1 submitted 20 July, 2026; originally announced July 2026.

Comments: 22 pages, 7 figures, authors are listed alphabetically by surname; update Figure 7 on page 15 due to arXiv format requirements

Cross-Domain Acceleration of Open Modification Search: From Commodity Platforms to Emerging Memory and Storage Devices

Authors: Sumukh Pinge, Chang Eun Song, Po-Kai Hsu, Zheyu Li, Ashkan Moradifirouzabadi, Yanru Chen, Xiangjin Wu, Wei-Chen Chen, Eric Pop, Shimeng Yu, H. -S. Philip Wong, Tajana Rosing, Mingu Kang

Abstract: Open modification search (OMS) in mass spectrometry (MS) is a data-intensive workload whose performance is dominantly limited by reference data movement rather than computation. Prior OMS accelerators have largely been evaluated in isolation, making it difficult to understand system-level trade-offs across platforms. This paper presents the first workload-driven, cross-platform survey of accelerat… ▽ More Open modification search (OMS) in mass spectrometry (MS) is a data-intensive workload whose performance is dominantly limited by reference data movement rather than computation. Prior OMS accelerators have largely been evaluated in isolation, making it difficult to understand system-level trade-offs across platforms. This paper presents the first workload-driven, cross-platform survey of accelerators for MS search by studying not only commodity platforms, but also emerging memory- and storage-centric architectures, including GPUs, near-storage FPGAs, DRAM near-memory processing, ReRAM/PCM in-memory processing, and 3D NAND/FeNAND in-storage processing, under consistent algorithmic and accuracy assumptions. Leveraging a binary hyperdimensional computing (HDC)-based OMS formulation that reduces similarity evaluation to lightweight bitwise primitives and tolerates device-level non-idealities, we enable a robust execution on memory-centric architectures despite device-level non-idealities and limited computing capability. Overall, this study identifies memory- and storage-centric architectures as a key architectural breakthrough for large-scale, high-speed search acceleration, delivering up to >100x speedup and >40,000x improvement in energy efficiency. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Comments: Accepted manuscript. Published in IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), Early Access, 2026. Sumukh Pinge and Chang Eun Song are co-first authors and contributed equally to this work

Journal ref: IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), Early Access, 2026

Who Will Become the Next Senior? How Generative AI Erodes the Development Pathway in Software Engineering

Authors: Sumin Yu, Taesup Moon

Abstract: Generative AI (GenAI) is reshaping software engineering, raising concerns about how the development pathway through which juniors become seniors is being eroded. While macro statistics show a decline in junior hiring and controlled studies demonstrate the effects of AI on individual task performance, the mechanisms through which GenAI reshapes early-career development in real organizational and ed… ▽ More Generative AI (GenAI) is reshaping software engineering, raising concerns about how the development pathway through which juniors become seniors is being eroded. While macro statistics show a decline in junior hiring and controlled studies demonstrate the effects of AI on individual task performance, the mechanisms through which GenAI reshapes early-career development in real organizational and educational contexts have not been thoroughly examined. Through 14 semi-structured interviews with juniors at the threshold of entering software engineering and senior software engineers in South Korea, analyzed using Reflexive Thematic Analysis, we reveal a foundational pattern of Absorption -- GenAI redirects entry-level work into senior-AI workflows -- and three consequences: (1) juniors losing the productive struggle through which expertise once developed; (2) the structural reproduction of this loss through collective normalization of GenAI use in university classrooms; and (3) the perceptual asymmetry between seniors and juniors that prevents either side from correcting these dynamics on their own. By extending learning theory and situated cognition to organizational and institutional scales, we argue that GenAI appears to be absorbing not just specific categories of tasks but also parts of the pathway through which the next generation of seniors is formed. Preserving this pathway will require deliberate institutional design across classrooms, workplaces, and the evaluation criteria for juniors. △ Less

Submitted 19 July, 2026; originally announced July 2026.

Comments: Accepted to AIES 2026

Isotonic Conformal Prediction

Authors: Daniel Bensimon, Sean Xiang Yu, Eric D. Kolaczyk, Archer Y. Yang

Abstract: A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its use in downstream decision-making. We consider two objectives for reliable uncertainty quantification: self-calibration, requiring a point prediction to be unbiased conditional on its own value, and prediction-conditional validity, requiring a prediction interval t… ▽ More A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its use in downstream decision-making. We consider two objectives for reliable uncertainty quantification: self-calibration, requiring a point prediction to be unbiased conditional on its own value, and prediction-conditional validity, requiring a prediction interval to attain nominal coverage conditional on the prediction. Self-Calibrating Conformal Prediction (SC-CP) attains both objectives exactly in finite samples, but requires refitting its calibrator for every candidate outcome, which is computationally prohibitive for continuous outcomes. We propose Isotonic Conformal Prediction (ICP), a framework that decouples calibration from prediction-set construction by fitting a single isotonic recalibration map and constructing prediction intervals within strata of similar recalibrated predictions. Within this framework we develop two procedures. Split Isotonic Conformal Prediction (SICP) attains prediction-conditional validity in finite samples and self-calibration asymptotically, at the computational cost of split conformal prediction. Transductive Isotonic Conformal Prediction (TICP) attains both objectives exactly in finite samples through a per-test-point inner loop that avoids refitting the isotonic calibrator. On synthetic heteroscedastic regression problems and a real-world healthcare-utilization dataset, both procedures match the coverage of SC-CP at substantially lower computational cost. △ Less

Submitted 18 July, 2026; originally announced July 2026.

A Survey on GNN-based Link Prediction: Techniques, Applications, and Challenges

Authors: Chengcheng Sun, Yajie Song, Cheng Zhai, Jiayun Tian, Jia Yang, Xiaobin Rui, Jian Zhang, Zhixiao Wang, Philip S. Yu

Abstract: Graph Neural Networks (GNNs) have emerged as the leading paradigm for link prediction, enabling the inference of missing connections and the anticipation of potential future links. However, existing reviews lack systematic exploration specifically targeting underlying GNN architectures and diverse graph structures. To address this critical gap, this paper provides a comprehensive review of GNN-bas… ▽ More Graph Neural Networks (GNNs) have emerged as the leading paradigm for link prediction, enabling the inference of missing connections and the anticipation of potential future links. However, existing reviews lack systematic exploration specifically targeting underlying GNN architectures and diverse graph structures. To address this critical gap, this paper provides a comprehensive review of GNN-based link prediction from a novel and dedicated GNN perspective. We propose an innovative taxonomy that categorizes recent advancements based on techniques and applications. From a technique perspective, we focus on key GNN encoder architectures, including GCN-based, GAE-based, GAT-based, and GFormer-based methods, discussing their strengths and limitations. From an application perspective, we highlight prominent use cases of link prediction in knowledge graphs and recommendation systems, demonstrating their real-world impact. In addition, we examine the current challenges and discuss promising future directions. △ Less

Submitted 28 April, 2026; originally announced July 2026.

Comments: Submmit to WIREs: Data Mining and Knowledge Discovery. This version of the article has been accepted, after peer review but is not the version of record. The final version will be available at: https://doi.org/10.1002/widm.70093. Paper list at Github: https://github.com/sunxiaobei/awesome-gnn-based-link-prediction

MSC Class: 68T07; 68R10 ACM Class: I.2.6; G.2.2; H.2.8; A.1

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation

Authors: Yi Wu, Junjie An, Xiao Liu, Yiqun Zhou, Yuechen Wu, Xiaoqing Guan, Shuyang Yu, You Wang, Guang Li

Abstract: In goal-directed embodied navigation, where an agent must locate a specified target in an unseen environment, 3D scene understanding and navigation reasoning must work in concert. Current approaches transmit 3D scene information to vision-language models (VLMs) through text, suggesting a representation gap in our tested configurations; a controlled ablation confirms that direct embedding-level tra… ▽ More In goal-directed embodied navigation, where an agent must locate a specified target in an unseen environment, 3D scene understanding and navigation reasoning must work in concert. Current approaches transmit 3D scene information to vision-language models (VLMs) through text, suggesting a representation gap in our tested configurations; a controlled ablation confirms that direct embedding-level transfer significantly outperforms the evaluated text serialization formats. We introduce SoftNav, which injects entity-level 3D continuous representations -- one token per detected object or frontier -- into a VLM's hidden space as soft tokens through a lightweight projector. With the 3D encoder and VLM frozen, only ~1,200 samples and ~17M trainable parameters are needed. On HM3D-OVON, SoftNav achieves 74.2%/68.3%/66.7% SR across three splits, surpassing all prior methods in both SR and SPL; the same navigation policy transfers zero-shot to GOAT-Bench (67.2% SR), SG3D (47.2% s-SR), and real-world robot deployment without retraining or architectural modification. Injecting 3D scene tokens directly into VLMs bridges the representation gap, enabling transferable navigation with minimal training. △ Less

Submitted 16 July, 2026; originally announced July 2026.

Comments: 8 pages, 6 figures. Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026