Showing 1–50 of 127 results for author: Ren, R

Online Service with Per-Batch Maximum Delay

Authors: Tianhang Lu, Runtian Ren, Shengcai Liu, Ke Tang

Abstract: We study online service with one maximum-waiting-time charge per service batch. Requests arrive at points of a finite metric, and a mobile server pays for its movement and, for each service walk, the maximum waiting time among the requests served by that walk. We distinguish elective service, where an encountered request may be left pending, from automatic service, where every encounter serves it.… ▽ More We study online service with one maximum-waiting-time charge per service batch. Requests arrive at points of a finite metric, and a mobile server pays for its movement and, for each service walk, the maximum waiting time among the requests served by that walk. We distinguish elective service, where an encountered request may be left pending, from automatic service, where every encounter serves it. Although the two semantics have different optimal schedule structures, we prove that their offline optimal values are equal. On a finite line and on an explicitly represented weighted tree, the common offline value is computable by polynomial-time dynamic programming, whereas exact optimization on arbitrary finite metrics is NP-hard. For the online problem, we prove a metric-independent group-trajectory certificate lemma that charges spatially separated request groups to two parity classes of time windows. It yields deterministic polynomial-time competitive ratios 10 on a line, 12 on a weighted tree, and 20 on an arbitrary finite metric, under both service semantics. With an exact metric-Steiner-tree oracle, the general-metric ratio improves to 12. The polynomial algorithm uses a half-scaled running maximum of terminal-MST weights; the running maximum is necessary because terminal MST weight is not monotone under new arrivals. A fixed two-point line gives a deterministic visible-service lower bound of 3 for every metric class above. Finally, when request locations are hidden until visited, dyadic exploration is 84-competitive on a known finite line. This phenomenon is line-specific: one hidden request gives deterministic and randomized lower bounds 3 and 2 on a line, while a d-leaf unit star gives lower bounds 2d-1 and d. △ Less

Submitted 19 August, 2026; originally announced August 2026.

Comments: 36 pages, 3 figures

FAM-DQ: A Dual-Quadrotor-Based Fully Actuated Aerial Manipulator for High-Torque Interaction

Authors: Xuwei Yang, Ruoyu Ren, Ziqian Guo

Abstract: Aerial physical interaction requires aerial manipulation platforms to generate large interaction forces and torques while maintaining precise end-effector control. However, conventional underactuated aerial manipulators suffer from strong position-attitude coupling, whereas fully actuated platform designs often face structural complexity, limited payload capacity, and insufficient torque output. T… ▽ More Aerial physical interaction requires aerial manipulation platforms to generate large interaction forces and torques while maintaining precise end-effector control. However, conventional underactuated aerial manipulators suffer from strong position-attitude coupling, whereas fully actuated platform designs often face structural complexity, limited payload capacity, and insufficient torque output. This paper presents FAM-DQ, a dual-quadrotor based fully actuated aerial manipulator designed for high-torque physical interaction tasks. By mounting two quadrotor propulsion modules at the ends of a central frame through passive joints, while using a gear-driven servo to regulate the pointing direction, FAM-DQ achieves decoupled $6$-DoF end-effector control with omnidirectional manipulation capability and enhanced torque output. Experiments including trajectory tracking, attitude tracking, static torque measurement, and screw driving validate the proposed design. FAM-DQ achieves a maximum torque of $1.019~\mathrm{N}\cdot\mathrm{m}$ with a total mass of $0.447~\mathrm{kg}$, corresponding to a torque-to-mass ratio of $2.28~\mathrm{N}\cdot\mathrm{m/kg}$. △ Less

Submitted 13 August, 2026; originally announced August 2026.

Comments: 7 pages, 7 figures

BOUND: Brief-Guided Corrective Preference Distillation at Search-Control Boundaries

Authors: Qingying Niu, Ruiyang Ren, Wayne Xin Zhao, Yaliang Li

Abstract: Large language model (LLM)-based deep search agents solve tasks through iterative retrieval and reasoning, but locally relevant evidence can cause persistent wrong-anchor drift, constraint drift, or local-topic drift. Existing methods supervise trajectories, outcomes, or steps, but rarely distinguish task-aligned continuations from locally plausible ones that reinforce drift. We propose BOUND, a b… ▽ More Large language model (LLM)-based deep search agents solve tasks through iterative retrieval and reasoning, but locally relevant evidence can cause persistent wrong-anchor drift, constraint drift, or local-topic drift. Existing methods supervise trajectories, outcomes, or steps, but rarely distinguish task-aligned continuations from locally plausible ones that reinforce drift. We propose BOUND, a brief-guided corrective preference distillation framework for persistent search drift. For each student-induced decision-time state, BOUND constructs a teacher-side search-state brief that preserves the original search target and key constraints while summarizing confirmed evidence, missing information, and drift status. Guided by the brief, the teacher determines whether the student's continuation contains a correctable local search-control error likely to affect subsequent decisions. Together with the rollout outcome, this assessment determines whether to construct a corrective contrast between a student-specific correction and the original continuation, or a termination contrast between a supported answer and an unnecessary retrieval continuation. Each validated state-matched preference pair operationalizes a search-control boundary. Direct preference optimization (DPO) distills these preferences into the student, while the brief and teacher-side computation remain confined to training. We evaluate BOUND on four multi-hop QA benchmarks and three deep-search benchmarks. Across the six benchmarks for which we reran baselines, BOUND leads on five datasets and 12 of 14 metrics. Under the same search-control interface and matched settings, BOUND outperforms Trajectory SFT by 5.6 EM points on Bamboogle and 4.8 accuracy points on BrowseComp-Plus. Code is available at https://github.com/RUCAIBox/BOUND. △ Less

Submitted 9 August, 2026; originally announced August 2026.

Comments: 15 pages

Online Multi-Level Aggregation with Per-Batch Maximum Delay

Authors: Tianhang Lu, Runtian Ren, Shengcai Liu, Ke Tang

Abstract: We study online multi-level aggregation on finite rooted trees with a per-batch maximum-delay objective. A service pays for a rooted subtree and for the maximum waiting time among the requests cleared by that service. We show that the offline optimum admits a consecutive-arrival-block normal form and can be computed by a polynomial-time dynamic program. The same dynamic program defines the deadlin… ▽ More We study online multi-level aggregation on finite rooted trees with a per-batch maximum-delay objective. A service pays for a rooted subtree and for the maximum waiting time among the requests cleared by that service. We show that the offline optimum admits a consecutive-arrival-block normal form and can be computed by a polynomial-time dynamic program. The same dynamic program defines the deadlines of a family of online algorithms, which we call DP-Envelope. Its deterministic endpoint is $2$-competitive. Sampling one global parameter with density $e^θ/(e-1)$ leads to an $e/(e-1)$-competitive randomized algorithm against an oblivious adversary. The deterministic guarantee matches the known fixed-node lower bound, and we prove a matching randomized lower bound. Thus, both guarantees are optimal on every nondegenerate rooted tree. We first develop the line metric as a warm-up, where the algorithm and its nested block partitions have a direct geometric interpretation. Finally, we show that the upper bounds extend to every realizable static service system with a normalized, nondecreasing, submodular joint service cost. △ Less

Submitted 20 August, 2026; v1 submitted 7 August, 2026; originally announced August 2026.

CyberNeuro: A Privacy-Preserving Agentic Workbench for Cohort-Scale Neuroimage and Clinical Data Analysis

Authors: Ran Ren, Junhong Tong, Yunxi Kong, Yiyao Chen, Yucheng Li, Kunhao Zhou, Shaoqi Wang, Yuxiang Tao, Shuheng Cao, Zhihao Fan, Marissa DiPiero, Tingting Dan, Guorong Wu

Abstract: Despite tremendous success in neuroimaging methodology, making large-scale, high-dimensional datasets ready for AI/ML applications remains a critical operational bottleneck. Conventional workflows require extensive manual effort across metadata curation, pipeline execution, post-processing quality control, and data management, a burden that disproportionately excludes laboratories with limited man… ▽ More Despite tremendous success in neuroimaging methodology, making large-scale, high-dimensional datasets ready for AI/ML applications remains a critical operational bottleneck. Conventional workflows require extensive manual effort across metadata curation, pipeline execution, post-processing quality control, and data management, a burden that disproportionately excludes laboratories with limited manpower and computational infrastructure. To address this real-world barrier, there is an urgent need for scalable, cost-effective computational platforms that democratize advanced neuroimaging analytics and accelerate discoveries in mental health and clinical translation. Capitalizing on multi-agent LLM breakthroughs, we introduce CyberNeuro, an agentic workbench with a tailored local LLM-model ('WandaMind') for automated neuroimaging and health-data analysis. Driven by four dedicated agents (Planner, Validator, Dispatcher, and Reporter) communicating via a secure MCP bridge and a pinned execution layer, CyberNeuro enables researchers to execute complex workflows using natural language while maintaining clinical-grade data privacy. On the public NeuroBench suite, CyberNeuro increases held-out domain accuracy from 40% to 69% over the baseline model. Beyond automated metrics, the platform integrates a human-in-the-loop verification panel to ensure rigorous biomedical quality control. Across the same end-to-end 10-batch cohort workflow suite, the local WandaMind configuration completed all tasks with an estimated aggregate token count of about 10.6% using WandaMind and 61.7% using cloud providers of token usage, compared to Neuroclaw, respectively. The platform and its production-ready modules are available at https://wanda-cyberbench.com. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Comments: 25 pages, 4 figures

ACM Class: I.2

Learning-Augmented and Randomized Algorithms for Line Aggregation with Delays

Authors: Tianhang Lu, Runtian Ren, Shengcai Liu, Ke Tang

Abstract: This paper studies learning-augmented and randomized online aggregation with delays on a line metric. We consider advice given as online suggested service lengths, and evaluate the algorithms in terms of robustness and consistency. For each $λ\in (0,1]$, we first propose a deterministic learning-augmented \textsc{Balance} algorithm that is $(4/λ+1/λ^2)$-robust and $(4+λ)$-consistent. We also propo… ▽ More This paper studies learning-augmented and randomized online aggregation with delays on a line metric. We consider advice given as online suggested service lengths, and evaluate the algorithms in terms of robustness and consistency. For each $λ\in (0,1]$, we first propose a deterministic learning-augmented \textsc{Balance} algorithm that is $(4/λ+1/λ^2)$-robust and $(4+λ)$-consistent. We also propose a randomized algorithm for the problem in the classical adversarial model, which is $(e+1)$-competitive against an oblivious adversary, improving over the deterministic $5$-competitive \textsc{Balance} benchmark~\cite{bienkowski2013chain}. Notably, this competitive ratio is even lower than the lower bound of $4$ for deterministic online algorithms. Moreover, we establish a lower bound of $e$ on the competitive ratio of randomized online algorithms, improving the previous lower bound of $e/(e-1)$. Besides, we combine the two ideas and obtain a randomized learning-augmented algorithm that is $(e/λ+1/λ^2)$-robust and $(e+λ)$-consistent. Finally, we conduct numerical experiments to complement our theoretical analysis and evaluate the empirical performance of our algorithms. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis

Authors: Xinhao Yao, Yuanzhuo Liu, Changhao Wang, Yunfei Yu, Haoran Tan, Yuyao Zhang, Ruifeng Ren, Minlong Peng, Yong Liu

Abstract: Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entangles retrieval quality, long-context comprehension, evidence verification, and tool-use decisions, making it difficult to determine whether a model truly knows when and how to delegate information seeking to search. To th… ▽ More Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entangles retrieval quality, long-context comprehension, evidence verification, and tool-use decisions, making it difficult to determine whether a model truly knows when and how to delegate information seeking to search. To this end: (1) We formalize this meta-capability as Delegation Intelligence in deep search and decompose it into complementary dimensions-Search Decision-Making (recognizing information insufficiency and deciding whether, when, and how to search) and Information Synthesis and Verification (aggregating evidence from multiple sources, judging source reliability, and synthesizing information under noisy, potentially adversarial conditions). (2) To enable disentangled and reproducible measurement, we develop a controllable synthesis pipeline built on document-grounded reverse engineering. This yields a general recipe for constructing controlled deep-search evaluations rather than a single fixed dataset. (3) As a concrete instantiation, we construct DelegSearchBench, together with a disentangled evaluation protocol that isolates each capability dimension by varying document composition and tool access. (4) Across representative models, we demonstrate that deep-search competence cannot be adequately characterized by final-answer accuracy alone... △ Less

Submitted 26 July, 2026; originally announced July 2026.

Comments: Work in Progress

The Cross-Domain Generalization Cost of Offensive Language Detection

Authors: Ruixing Ren, Junhui Zhao, Xiaoke Sun, Qiuping Li

Abstract: Offensive language detection models generally suffer performance degradation when deployed across datasets and across languages, yet most existing studies stop at reporting this phenomenon and lack a systematic methodology for decomposing the causes of degradation into attributable components and quantifying the cost of remediation. This paper proposes a diagnosis and optimization framework compos… ▽ More Offensive language detection models generally suffer performance degradation when deployed across datasets and across languages, yet most existing studies stop at reporting this phenomenon and lack a systematic methodology for decomposing the causes of degradation into attributable components and quantifying the cost of remediation. This paper proposes a diagnosis and optimization framework composed of three coordinated technical components. First, a zero-shot transfer loss decomposition that separates the performance degradation from OLID to MLMA into two independently measurable components, namely dataset effect and language effect. Second, a controlled fine-tuning protocol that quantifies both adaptation efficiency and the hidden damage inflicted on the source task by comparing few shot learning curves under continued fine-tuning and cold-start starting points. Third, three joint training strategies incorpo rating temperature sampling and experience replay, which offer a controllable Pareto trade-off between improving multilingual capability and preserving source-task performance. Experiments built on this framework show that the dataset effect dominates the zero-shot transfer loss and substantially outweighs the language effect. Few-shot adaptation without a replay mechanism, though data-efficient, inflicts source task damage 4 to 9 times greater than that of the joint training strategies, and its damage magnitude is highly unstable. The three joint training strategies trade 3.2 to 4.1 percentage points of source-task performance for 8.1 to 42.6 percentage points of multilingual capability gain, forming a clear and controllable Pareto trade-off. △ Less

Submitted 26 July, 2026; originally announced July 2026.

Comments: 8 pages, 6 figures

MSC Class: 68T50 ACM Class: I.2.7; I.2.6

TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis

Authors: Isabel Xu, Cynthia Xu, Rachel Ren, Cong Guo, Jiacheng Ding

Abstract: Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence re… ▽ More Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence reasoner (Qwen2.5, 0.5B-14B-4bit, with Mistral-7B and Phi-3.5-mini cross-family checks). A three-way Semantic Divergence Index (SDI) measures pairwise disagreement across granularities and routes each query accordingly. Our central finding is the critic plateau: when the LLM is re-tasked as a critic over the smaller agents' outputs, F1 plateaus at ~0.87 across 1.5B-7B Qwen (bootstrap 95% CIs overlap), while a same-size 3-persona vote drops to F1=0.66, which is driven by granularity-stratified diversity. Three corollaries follow from the same SDI signal: (i) a Shared Consensus Dictionary on multilingual sentence-BERT answers 95% of Chinese queries from an English cache at F1=0.99 -- cross-border canonicalization at zero marginal cost; (ii) SDI doubles as a post-hoc LLM-hallucination detector at AUC=0.90; (iii) the SDI single-stage strategy attains the best risk-adjusted return (Sharpe=3.50) on a 20-ticker back-test, dominating both always-FinBERT (1.36) and always-LLM (0.11). At 10M-user scale, TriAgent saves $9.3M/year vs. a GPT-4o-mini baseline. Code, lexicons, and the SCD are released. △ Less

Submitted 22 July, 2026; originally announced July 2026.

Cascading versus Joint Modeling for Hierarchical Offensive Language Detection

Authors: Ruixing Ren, Junhui Zhao, Xiaoke Sun

Abstract: Fine-grained offensive language detection organizes labels into a hierarchical structure, for which two modeling paradigms exist: cascaded decomposition and joint multi-task modeling. Prior work rarely provides a direct, controlled comparison of the two paradigms in terms of accuracy, parameter count, and inference latency, and rarely verifies whether a chosen class-imbalance handling strategy is… ▽ More Fine-grained offensive language detection organizes labels into a hierarchical structure, for which two modeling paradigms exist: cascaded decomposition and joint multi-task modeling. Prior work rarely provides a direct, controlled comparison of the two paradigms in terms of accuracy, parameter count, and inference latency, and rarely verifies whether a chosen class-imbalance handling strategy is actually optimal. This paper proposes a three-level cascaded detection system whose training strategy is customized per subtask, together with two verification mechanisms. First, a controlled ablation study determines the best class-imbalance handling strategy for each subtask. Second, a joint multi-task model with a shared encoder is trained as an architectural control, yielding real measurements along the dimensions of accuracy, parameter count, and inference latency. Experiments show that the cascaded system attains macro-F1 scores of 0.795, 0.716, and 0.557 on the three subtasks of the official test set. The ablation study reveals that configuring the loss function purely by imbalance-severity intuition is suboptimal; reconfiguring based on the ablation results improves both performance and stability. End-to-end cascade evaluation shows that roughly one-fifth of the errors in the cascade pipeline originate from the first-stage filter and cannot be corrected by subsequent stages. Relative to the joint multi-task model, the cascaded architecture achieves higher accuracy on all three subtasks, with a 7.1-point macro-F1 gain on the most severely imbalanced subtask, at the cost of three times the parameters and 1.67 times the inference latency. Together, these results establish an explicit, quantifiable trade-off between the accuracy advantage of cascaded architectures and their deployment cost. △ Less

Submitted 18 July, 2026; originally announced July 2026.

MSC Class: 68T50 ACM Class: I.2.7; H.3.1

CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking

Authors: Ruilong Ren, Songsheng Cheng, Yunpeng Zhou, Hanxuan Chen, Xiangyue Wang, Tianle Zeng, Shuai Yuan, Binbo Li, Hanzhong Guo, Ji Pei, Da Zhang, Kangli Wang

Abstract: Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously. Existing Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degrades when buildings, vegetation, or roadside objects block the line of sight. During sustained occlu… ▽ More Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously. Existing Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degrades when buildings, vegetation, or roadside objects block the line of sight. During sustained occlusion, a policy may lose the target state, execute actions toward an incorrect region, and amplify this error through subsequent observations until re-acquisition becomes impossible. To this end, we present CosFly-VLA, a spatially aware VLA model that jointly grounds the target, estimates its visibility, and generates continuous flight actions through a structured prediction interface. To train this policy, we use a large-scale recipe over diverse data sources. Spatially Grounded Continued Pretraining (CPT) on a 500k mixed pool injects UAV-view depth, distance, and 3-D spatial reasoning. A three-stage Curriculum-based Supervised Fine-Tuning (SFT) process then specializes the tracker through multi-head warm-up followed by two-stage curriculum learning over natural and hard / long-occlusion data. Chain-of-Thought (CoT) training subsequently teaches recovery-oriented reasoning traces before structured answers. Finally, a closed-loop Reinforcement Learning (RL) stage optimizes tracking behavior with a multi-component reward covering stand-off tracking, grounding quality, collision avoidance, and task success. Relative to OpenVLA, CosFly-VLA-0.8B reduces open-loop Average Displacement Error (ADE) by 34.1% on seen-test and 35.3% on unseen-test. Closed-loop optimization improves Success Rate (SR) by 29.8% and 2.5%, respectively. These results demonstrate progress from visible-frame imitation toward spatially grounded action-closed-loop control, evaluated under a shared oracle state history. △ Less

Submitted 16 July, 2026; originally announced July 2026.

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift

Authors: Dipesh Tharu Mahato, Rachel Ren

Abstract: Visual shifts can cause a vision-language-action policy to fail after initially plausible behavior. We ask whether OpenVLA's internal activations contain signals associated with the steps before failure. We freeze the policy, record one MLP activation per LIBERO-10 step, and fit two linear monitors. Occlusion reduces task success from $57\%$ to $17\%$. Within failed matched-reset trajectories, a l… ▽ More Visual shifts can cause a vision-language-action policy to fail after initially plausible behavior. We ask whether OpenVLA's internal activations contain signals associated with the steps before failure. We freeze the policy, record one MLP activation per LIBERO-10 step, and fit two linear monitors. Occlusion reduces task success from $57\%$ to $17\%$. Within failed matched-reset trajectories, a layer-16 logistic probe attains AUROC $0.972$ and AUPRC $0.352$, whereas action disagreement attains AUROC $0.496$. Without refitting, the occlusion-trained probe reaches AUROC $0.689$ on failed camera-jitter episodes. In a calibration check, however, the same layer-16 monitor averages 3.32 warning onsets per clean episode. This contrast shows that strong retrospective discrimination does not imply operationally quiet warning behavior. Because fitting and evaluation share tasks, resets, and seed, these results establish retrospective separability rather than prediction on independent episodes. △ Less

Submitted 12 August, 2026; v1 submitted 28 June, 2026; originally announced June 2026.

Comments: 16 pages, 2 figures, 8 tables

Cross-Platform Chinese Offensive Comment Detection via Dual-Threshold Hard Example Mining

Authors: Ruixing Ren, Junhui Zhao, Fangfang Wang

Abstract: Cross-platform deployment of offensive comment detection for Chinese social media suffers performance degradation. The paper proposes a dual-threshold hard mining method to address this. First, the clean-Chinese-base RoBERTa is finetuned on COLD to establish a binary baseline for fair comparison. Second, a three-class fine-labeled test set covering Weibo, Xiaohongshu, Tieba, and Zhihu is construct… ▽ More Cross-platform deployment of offensive comment detection for Chinese social media suffers performance degradation. The paper proposes a dual-threshold hard mining method to address this. First, the clean-Chinese-base RoBERTa is finetuned on COLD to establish a binary baseline for fair comparison. Second, a three-class fine-labeled test set covering Weibo, Xiaohongshu, Tieba, and Zhihu is constructed, domain distances from the source are quantified using Jaccard and Proxy-A Distance, as well as the degradation bottleneck of the baseline under domain shift is systematically revealed. Herein, a dual threshold hard example mining strategy is proposed. High- and low-confidence error-prone samples are filtered from unlabeled corpora by prediction confidence. The model is secondarily finetuned under implicit contexts with merely a small set of manually labeled hard examples, realizing low-cost cross-platform domain adaptation. Experiments reveal significant performance gains of the optimized model across four platforms. △ Less

Submitted 25 June, 2026; originally announced June 2026.

Comments: 10 pages, 7 figures

MSC Class: 68T50; 68U15; 91F10 ACM Class: I.2.7; I.2.6; H.3.4

Learning-Augmented Algorithms for Online Vertex Cover

Authors: Tianhang Lu, Runtian Ren, Shengcai Liu

Abstract: This paper studies learning-augmented online weighted vertex cover with local advice and a tradeoff parameter $λ\in (0,1)$. We consider two graph settings: bipartite graphs and general graphs. In both settings, the online algorithm must maintain a feasible vertex cover under irrevocable decisions. We show that these problems admit the same robustness--consistency tradeoffs as learning-augmented sk… ▽ More This paper studies learning-augmented online weighted vertex cover with local advice and a tradeoff parameter $λ\in (0,1)$. We consider two graph settings: bipartite graphs and general graphs. In both settings, the online algorithm must maintain a feasible vertex cover under irrevocable decisions. We show that these problems admit the same robustness--consistency tradeoffs as learning-augmented ski rental. For the bipartite graph model, we give a randomized algorithm that is $\frac{1}{1-e^{-λ}}$-robust and $\fracλ{1-e^{-λ}}$-consistent. For the general graph model, we give a deterministic algorithm that is $(1+\frac{1}λ)$-robust and $(1+λ)$-consistent. We prove that the tradeoffs above are optimal in both settings. We also validate the proposed algorithms through experiments on synthetic and real-world datasets. △ Less

Submitted 30 July, 2026; v1 submitted 22 June, 2026; originally announced June 2026.

Speculative Pipeline Decoding: Higher-Accuracy Drafting with Hidden Latency via Pipeline Parallelism

Authors: Yijiong Yu, Huazheng Wang, Shuai Yuan, Ruilong Ren, Ji Pei

Abstract: Speculative Decoding (SD) accelerates low-concurrency LLM inference with a draft-then-verify paradigm. Mainstream methods, however, rely on multi-token prediction, which incurs compounding prediction difficulty and exposed draft latency. We propose Speculative Pipeline Decoding (SPD), which partitions the target LLM into $n$ pipeline stages so that $n$ tokens of a single sequence advance in parall… ▽ More Speculative Decoding (SD) accelerates low-concurrency LLM inference with a draft-then-verify paradigm. Mainstream methods, however, rely on multi-token prediction, which incurs compounding prediction difficulty and exposed draft latency. We propose Speculative Pipeline Decoding (SPD), which partitions the target LLM into $n$ pipeline stages so that $n$ tokens of a single sequence advance in parallel. To keep the pipeline saturated, a Pipeline Draft Module (PDM) aggregates multi-depth target features to predict the next token and runs concurrently with each pipeline step, yielding bounded prediction difficulty, higher acceptance, and hidden draft latency. Experiments show that SPD achieves higher theoretical and wall-clock speedup than EAGLE-3 at moderate pipeline width, while more aggressive widths still leave room for further gains. Our code is available at https://github.com/yuyijiong/speculative_pipeline_decoding △ Less

Submitted 26 July, 2026; v1 submitted 29 May, 2026; originally announced May 2026.

CosFly: Plan in the Matrix, Fly in the World

Authors: Hanxuan Chen, Xiangyue Wang, Songsheng Cheng, Ruilong Ren, Jie Zheng, Shuai Yuan, Tianle Zeng, Hanzhong Guo, Binbo Li, Kangli Wang, Ji Pei

Abstract: We present CosFly, a box-structured planning and multimodal simulation pipeline for aerial tracking, together with CosFly-Track, a large-scale UAV dataset for dynamic target tracking across diverse environments including urban centers, highways, rural landscapes, forests, and coastal towns. In our current implementation on CARLA, CosFly provides a modular 7-step construction pipeline that converts… ▽ More We present CosFly, a box-structured planning and multimodal simulation pipeline for aerial tracking, together with CosFly-Track, a large-scale UAV dataset for dynamic target tracking across diverse environments including urban centers, highways, rural landscapes, forests, and coastal towns. In our current implementation on CARLA, CosFly provides a modular 7-step construction pipeline that converts complex 3D worlds into structured obstacle representations for planning, then projects the resulting trajectories back into multi-modal sensor data -- including RGB images, high-precision depth maps, and semantic segmentation masks -- paired with natural language navigation instructions. A key feature is the support for configurable fixed-FOV zoom levels (one FOV setting drawn per trajectory and held constant throughout), enabling simulation of various focal lengths through camera-intrinsic adjustments. The pipeline covers the complete workflow from 3D map export through grid simplification, pedestrian and drone trajectory planning, multi-modal rendering with 6-DOF pose annotations, quality inspection, and teacher-student caption generation. We analyze two trajectory-planning paradigms for aerial target tracking: a conventional two-stage pipeline with front-end candidate generation and backend refinement, and a direct gradient-based formulation that optimizes multiple tracking constraints in a single objective. The public CosFly-Track release contains 250 validated trajectories and approximately 100,000 rendered images with complete 6-DOF drone pose annotations (position x, y, z and orientation yaw, pitch, roll). Together, the pipeline and dataset establish a scalable foundation for aerial-ground collaborative research, supporting dynamic target tracking, UAV navigation, and multi-modal perception across diverse environments. △ Less

Submitted 18 May, 2026; originally announced May 2026.

CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization

Authors: Xiangyue Wang, Hanxuan Chen, Songsheng Cheng, Ruilong Ren, Jie Zheng, Shuai Yuan, Tianle Zeng, Hanzhong Guo, Kangli Wang, Ji Pei

Abstract: Recent aerial vision-language navigation (VLN) datasets have grown rapidly, but they primarily address goal-oriented navigation to static destinations, leaving UAV visual tracking -- continuously following a moving target while maintaining visibility -- largely without dedicated training data. We introduce CosFlyTrack, a large-scale multi-modal dataset and scalable generation pipeline for UAV visu… ▽ More Recent aerial vision-language navigation (VLN) datasets have grown rapidly, but they primarily address goal-oriented navigation to static destinations, leaving UAV visual tracking -- continuously following a moving target while maintaining visibility -- largely without dedicated training data. We introduce CosFlyTrack, a large-scale multi-modal dataset and scalable generation pipeline for UAV visual tracking in urban environments. The dataset provides approximately 12,000 expert and perturbed UAV trajectories generated from 6,000 pedestrian paths, comprising 2.4 million timesteps (approximately 334 hours) with seven aligned data channels: RGB, metric depth, semantic segmentation, six-degree-of-freedom drone pose, target state with visibility flag, bilingual (Chinese-English) instructions, and trajectory-pair metadata. To generate high-quality expert trajectories, we develop MuCO, a multi-constraint optimizer that plans directly in continuous three-dimensional space with BVH-accelerated collision and visibility queries, jointly enforcing target visibility, viewpoint quality, collision avoidance, smoothness, and kinematic feasibility, avoiding the discretization artifacts and post-hoc smoothing of grid-based planners. Fine-tuning experiments on seven vision-language models show that CosFlyTrack improves tracking performance to 78.3 to 95.6 percent SR@1 meter, a 53 to 69 percentage point gain over zero-shot baselines, supporting the dataset as a training resource for dynamic target-following agents. The dataset is publicly available at https://huggingface.co/datasets/AutelRobotics/CosFly; evaluation scripts and pre-trained checkpoints are hosted at https://huggingface.co/AutelRobotics/CosFly-Track. △ Less

Submitted 20 May, 2026; v1 submitted 17 May, 2026; originally announced May 2026.

Kaczmarz Linear Attention

Authors: Jiaxuan Zou, Ruifeng Ren, Yong Liu

Abstract: Long-context language modeling remains central to modern sequence modeling, but the quadratic cost of Transformer attention makes scaling computationally prohibitive. Linear recurrent models address this bottleneck by compressing the context into a fixed-size state, making the rule that forgets, writes, and edits information a central design problem. To address state maintenance, Gated DeltaNet (G… ▽ More Long-context language modeling remains central to modern sequence modeling, but the quadratic cost of Transformer attention makes scaling computationally prohibitive. Linear recurrent models address this bottleneck by compressing the context into a fixed-size state, making the rule that forgets, writes, and edits information a central design problem. To address state maintenance, Gated DeltaNet (GDN) combines gated state decay with delta-rule residual writes, using a learnable coefficient to balance forgetting and update magnitude. However, this coefficient is learned empirically rather than derived from the underlying objective, which can lead to suboptimal update magnitudes. We revisit the online-regression objective underlying GDN and, inspired by the Kaczmarz projection method, derive the key-norm-normalized dynamic step size $β_t = η_t / (\|k_t\|_2^2 + ε)$ for residual updates. We propose Kaczmarz Linear Attention (KLA), a one-scalar modification of GDN that preserves the state shape, gates, linear recurrence, and chunkwise parallel algorithm. At the 0.4B scale with a 1B-token budget, KLA achieves the lowest validation perplexity among evaluated linear-time baselines, 8.09 versus 8.50 for GDN, and remains stable up to 65K tokens. On controlled tasks, KLA reaches 100% on single-needle-in-a-haystack retrieval, improves 8x multi-query associative recall by 7.03 points over GDN, and delivers 2.1x higher decode throughput at 32K context. These results suggest that the key-norm-normalized Kaczmarz coefficient is a first-order design axis for delta-rule sequence models: it improves accuracy, extrapolation, and decoding efficiency without changing the recurrent state or hardware kernel. △ Less

Submitted 8 May, 2026; originally announced May 2026.

ArguMath: AI-Simulated Environment for Pre-Service Teacher Training in Orchestrating Classroom Mathematics Argumentation

Authors: Jiwon Chun, Yuling Zhuang, Armanto Sutedjo, Colin Xu, Rong Ren, Meng Xia

Abstract: Facilitating productive mathematical argumentation, especially asking rational questions, is essential yet remains challenging for pre-service mathematics teachers (PMTs), who often have limited opportunities to apply abstract theoretical knowledge in authentic practice. At the same time, recent advances in large language models (LLMs) have expanded the potential for simulating students in educati… ▽ More Facilitating productive mathematical argumentation, especially asking rational questions, is essential yet remains challenging for pre-service mathematics teachers (PMTs), who often have limited opportunities to apply abstract theoretical knowledge in authentic practice. At the same time, recent advances in large language models (LLMs) have expanded the potential for simulating students in educational settings, enabling low-risk environments for instructional practice. To inform the design of a system that supports PMTs in orchestrating classroom argumentation, we conducted a formative study with eight experienced mathematics teachers to identify key design requirements, including personalization, realistic simulations, structured reflection, and ease of use. Building on these requirements, we developed ArguMath, an AI-simulated classroom environment that supports PMTs in practicing the orchestration of mathematical argumentation. ArguMath comprises three core components: (1) customization of classroom settings; (2) simulation of classroom discussions with AI-based students grounded in authentic transcripts and augmented with real-time instructional suggestions; and (3) structured reflection through discourse annotation and overall feedback. Results from an exploratory user study with seven PMTs, complemented by interviews with four experienced teachers, indicate that ArguMath has the potential to support PMTs' classroom orchestration skills, particularly theory-aligned questioning strategies. △ Less

Submitted 24 April, 2026; originally announced April 2026.

ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation

Authors: Qingying Niu, Yuhao Wang, Ruiyang Ren, Bohui Fang, Wayne Xin Zhao

Abstract: Retrieval-augmented generation (RAG) remains unreliable in long-form settings, where retrieved evidence is noisy or contradictory, making it difficult for RAG pipelines to maintain factual consistency. Existing approaches focus on retrieval expansion or verification during generation, leaving conflict resolution entangled with generation. To address this limitation, we propose ArbGraph, a framewor… ▽ More Retrieval-augmented generation (RAG) remains unreliable in long-form settings, where retrieved evidence is noisy or contradictory, making it difficult for RAG pipelines to maintain factual consistency. Existing approaches focus on retrieval expansion or verification during generation, leaving conflict resolution entangled with generation. To address this limitation, we propose ArbGraph, a framework for pre-generation evidence arbitration in long-form RAG that explicitly resolves factual conflicts. ArbGraph decomposes retrieved documents into atomic claims and organizes them into a conflict-aware evidence graph with explicit support and contradiction relations. On top of this graph, we introduce an intensity-driven iterative arbitration mechanism that propagates credibility signals through evidence interactions, enabling the system to suppress unreliable and inconsistent claims before final generation. In this way, ArbGraph separates evidence validation from text generation and provides a coherent evidence foundation for downstream long-form generation. We evaluate ArbGraph on two widely used long-form RAG benchmarks, LongFact and RAGChecker, using multiple large language model backbones. Experimental results show that ArbGraph consistently improves factual recall and information density while reducing hallucinations and sensitivity to retrieval noise. Additional analyses show that these gains are evident under conflicting or ambiguous evidence, highlighting the effectiveness of evidence-level conflict resolution for improving the reliability of long-form RAG. The implementation is publicly available at https://github.com/1212Judy/ArbGraph. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Comments: 23 pages, 4 figures

Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inference

Authors: Nenad Banfic, David Fan, Kunal Vaishnavi, Sam Kemp, Sunghoon Choi, Rui Ren, Sayan Shaw, Meng Tang

Abstract: Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic empirical study of state-of-the-art ASR architectures, encompassing encoder-decoder, transducer, and LLM-based paradigms, evaluated across batch, chunked, and streami… ▽ More Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic empirical study of state-of-the-art ASR architectures, encompassing encoder-decoder, transducer, and LLM-based paradigms, evaluated across batch, chunked, and streaming inference modes. Through a comprehensive benchmark of over 50 configurations spanning OpenAI Whisper, NVIDIA Nemotron, Parakeet TDT, Canary, Conformer Transducer, and Qwen3-ASR, we identify NVIDIA's Nemotron Speech Streaming as the strongest candidate for real-time English streaming on resource-constrained hardware. We then re-implement the complete streaming inference pipeline in ONNX Runtime and conduct a controlled evaluation of multiple post-training quantization strategies, including importance-weighted k-quant, mixed-precision schemes, and round-to-nearest quantization, combined with graph-level operator fusion. These optimizations reduce the model from 2.47 GB to as little as 0.67 GB while maintaining word error rate (WER) within 1% absolute of the full-precision PyTorch baseline. Our recommended configuration, the int4 k-quant variant, achieves 8.20% average streaming WER across eight standard benchmarks, running comfortably faster than real-time on CPU with 0.56 s algorithmic latency, establishing a new quality-efficiency Pareto point for on-device streaming ASR. △ Less

Submitted 19 April, 2026; v1 submitted 15 April, 2026; originally announced April 2026.

Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap

Authors: Hanxuan Chen, Jie Zheng, Siqi Yang, Tianle Zeng, Siwei Feng, Songsheng Cheng, Ruilong Ren, Hanzhong Guo, Shuai Yuan, Xiangyue Wang, Kangli Wang, Ji Pei

Abstract: Vision-and-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) represents a pivotal challenge in embodied artificial intelligence, focused on enabling UAVs to interpret high-level human commands and execute long-horizon tasks in complex 3D environments. This paper provides a comprehensive and structured survey of the field, from its formal task definition to the current state of the art. We… ▽ More Vision-and-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) represents a pivotal challenge in embodied artificial intelligence, focused on enabling UAVs to interpret high-level human commands and execute long-horizon tasks in complex 3D environments. This paper provides a comprehensive and structured survey of the field, from its formal task definition to the current state of the art. We establish a methodological taxonomy that charts the technological evolution from early modular and deep learning approaches to contemporary agentic systems driven by large foundation models, including Vision-Language Models (VLMs), Vision-Language-Action (VLA) models, and the emerging integration of generative world models with VLA architectures for physically-grounded reasoning. The survey systematically reviews the ecosystem of essential resources simulators, datasets, and evaluation metrics that facilitates standardized research. Furthermore, we conduct a critical analysis of the primary challenges impeding real-world deployment: the simulation-to-reality gap, robust perception in dynamic outdoor settings, reasoning with linguistic ambiguity, and the efficient deployment of large models on resource-constrained hardware. By synthesizing current benchmarks and limitations, this survey concludes by proposing a forward-looking research roadmap to guide future inquiry into key frontiers such as multi-agent swarm coordination and air-ground collaborative robotics. △ Less

Submitted 15 April, 2026; originally announced April 2026.

ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache

Authors: Shao Wang, Rui Ren, Lin Gui

Abstract: The serving paradigm of large language models (LLMs) is rapidly shifting towards complex multi-agent workflows where specialized agents collaborate over massive shared contexts. While Low-Rank Adaptation (LoRA) enables the efficient co-hosting of these specialized agents on a single base model, it introduces a critical memory footprint bottleneck during serving. Specifically, unique LoRA activatio… ▽ More The serving paradigm of large language models (LLMs) is rapidly shifting towards complex multi-agent workflows where specialized agents collaborate over massive shared contexts. While Low-Rank Adaptation (LoRA) enables the efficient co-hosting of these specialized agents on a single base model, it introduces a critical memory footprint bottleneck during serving. Specifically, unique LoRA activations cause Key-Value (KV) cache divergence across agents, rendering traditional prefix caching ineffective for shared contexts. This forces redundant KV cache maintenance, rapidly saturating GPU capacity and degrading throughput. To address this challenge, we introduce ForkKV, a serving system for multi-LoRA agent workflows centered around a novel memory management paradigm in OS: fork with copy-on-write (CoW). By exploiting the structural properties of LoRA, ForkKV physically decouples the KV cache into a massive shared component (analogous to the parent process's memory pages) and lightweight agent-specific components (the child process's pages). To support this mechanism, we propose a DualRadixTree architecture that allows newly forked agents to inherit the massive shared cache and apply CoW semantics for their lightweight unique cache. Furthermore, to guarantee efficient execution, we design ResidualAttention, a specialized kernel that reconstructs the disaggregated KV cache directly within on-chip SRAM. Comprehensive evaluations across diverse language models and practical datasets of different tasks demonstrate that ForkKV achieves up to 3.0x the throughput of state-of-the-art multi-LoRA serving systems with a negligible impact on generation quality. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Adaptive Multi-Dimensional Coordinated Comprehensive Routing Scheme for IoV

Authors: Ruixing Ren, Minqi Tao, Junhui Zhao, Qiuping Li, Xiaoke Sun

Abstract: The characteristics of high-speed node movement and dynamic topology changes pose great challenges to the design of internet of vehicles (IoV) routing protocols. Existing schemes suffer from common problems such as insufficient adaptability and lack of global consideration, making it difficult to achieve a globally optimal balance between routing reliability, real-time performance and transmission… ▽ More The characteristics of high-speed node movement and dynamic topology changes pose great challenges to the design of internet of vehicles (IoV) routing protocols. Existing schemes suffer from common problems such as insufficient adaptability and lack of global consideration, making it difficult to achieve a globally optimal balance between routing reliability, real-time performance and transmission efficiency. This paper proposes an adaptive multi-dimensional coordinated comprehensive routing scheme for IoV environments. A complete IoV system model including network topology, communication links, hierarchical congestion and transmission delay is first constructed, the routing problem is abstracted into a single-objective optimization model with multiple constraints, and a single-hop link comprehensive routing metric integrating link reliability, node local load, network global congestion and link stability is defined. Second, an intelligent transmission switching mechanism is designed: candidate nodes are screened through dual criteria of connectivity and progressiveness, a dual decision-making of primary and backup paths and a threshold switching strategy are introduced to avoid link interruption and congestion, and an adaptive update function is constructed to dynamically adjust weight coefficients and switching thresholds to adapt to changes in network status. Simulation results show that the proposed scheme can effectively adapt to the high dynamic topology and network congestion characteristics of IoV, perform excellently in key indicators such as routing interruption times, packet delivery rate and end-to-end delay, and its comprehensive performance is significantly superior to traditional routing schemes. △ Less

Submitted 29 March, 2026; originally announced March 2026.

Comments: 8 pages, 8 figures. An adaptive multi-dimensional coordinated comprehensive routing scheme for IoV environments

ACM Class: F.2.2; I.2.7; C.2.1

Emulating Clinician Cognition via Self-Evolving Deep Clinical Research

Authors: Ruiyang Ren, Yuhao Wang, Yunsen Liang, Lan Luo, Jing Liu, Haifeng Wang, Cong Feng, Yinan Zhang, Chunyan Miao, Ji-Rong Wen, Wayne Xin Zhao

Abstract: Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while lacking auditable mechanisms for governed improvement. We developed DxEvolve, a self-evolving diagnostic agent that bridg… ▽ More Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while lacking auditable mechanisms for governed improvement. We developed DxEvolve, a self-evolving diagnostic agent that bridges these gaps through an interactive deep clinical research workflow. The framework autonomously requisitions examinations and continually externalizes clinical experience from increasing encounter exposure as diagnostic cognition primitives. On the MIMIC-CDM benchmark, DxEvolve improved diagnostic accuracy by 11.2% on average over backbone models and reached 90.4% on a reader-study subset, comparable to the clinician reference (88.8%). DxEvolve improved accuracy on an independent external cohort by 10.2% (categories covered by the source cohort) and 17.1% (uncovered categories) compared to the competitive method. By transforming experience into a governable learning asset, DxEvolve supports an accountable pathway for the continual evolution of clinical AI. △ Less

Submitted 11 March, 2026; originally announced March 2026.

Tacmap: Bridging the Tactile Sim-to-Real Gap via Geometry-Consistent Penetration Depth Map

Authors: Lei Su, Zhijie Peng, Renyuan Ren, Shengping Mao, Juan Du, Kaifeng Zhang, Xuezhou Zhu

Abstract: Vision-Based Tactile Sensors (VBTS) are essential for achieving dexterous robotic manipulation, yet the tactile sim-to-real gap remains a fundamental bottleneck. Current tactile simulations suffer from a persistent dilemma: simplified geometric projections lack physical authenticity, while high-fidelity Finite Element Methods (FEM) are too computationally prohibitive for large-scale reinforcement… ▽ More Vision-Based Tactile Sensors (VBTS) are essential for achieving dexterous robotic manipulation, yet the tactile sim-to-real gap remains a fundamental bottleneck. Current tactile simulations suffer from a persistent dilemma: simplified geometric projections lack physical authenticity, while high-fidelity Finite Element Methods (FEM) are too computationally prohibitive for large-scale reinforcement learning. In this work, we present Tacmap, a high-fidelity, computationally efficient tactile simulation framework anchored in volumetric penetration depth. Our key insight is to bridge the tactile sim-to-real gap by unifying both domains through a shared deform map representation. Specifically, we compute 3D intersection volumes as depth maps in simulation, while in the real world, we employ an automated data-collection rig to learn a robust mapping from raw tactile images to ground-truth depth maps. By aligning simulation and real-world in this unified geometric space, Tacmap minimizes domain shift while maintaining physical consistency. Quantitative evaluations across diverse contact scenarios demonstrate that Tacmap's deform maps closely mirror real-world measurements. Moreover, we validate the utility of Tacmap through an in-hand rotation task, where a policy trained exclusively in simulation achieves zero-shot transfer to a physical robot. △ Less

Submitted 12 May, 2026; v1 submitted 25 February, 2026; originally announced February 2026.

Comments: 8 pages

Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspective

Authors: Weiyu Kong, Yun Lin, Xiwen Teoh, Duc-Minh Nguyen, Ruofei Ren, Jiaxin Chang, Haoxu Hu, Haoyu Chen

Abstract: Large Language Models (LLMs) have significantly improved programming efficiency by translating natural language into code, yet their performance deteriorates when handling large-scale, multi-modal requirement documents containing hundreds of scenarios, often producing incorrect implementations or missing critical constraints. To address this challenge, we propose ARC (Agentic Requirement Compilati… ▽ More Large Language Models (LLMs) have significantly improved programming efficiency by translating natural language into code, yet their performance deteriorates when handling large-scale, multi-modal requirement documents containing hundreds of scenarios, often producing incorrect implementations or missing critical constraints. To address this challenge, we propose ARC (Agentic Requirement Compilation), a framework that compiles DSL-based requirement documents into runnable software systems while automatically generating modular software architecture, comprehensive test suites, and traceability across requirements, design, and code. ARC adopts a bidirectional test-driven agentic workflow, combining a top-down architecture design phase with a bottom-up implementation phase to ensure that generated code satisfies synthesized tests. We evaluate ARC on six runnable web system benchmarks and the AppForge benchmark of 101 mobile app generation tasks. Across three independent trials, ARC consistently outperforms state-of-the-art LLM-based baselines, achieving 50.6% more GUI tests passed on average for web systems, a 100% compilation success rate, and a 68.3% test pass rate on AppForge. A user study with 21 participants further shows that users with limited programming experience can write DSL-based requirement documents containing up to 174 scenarios within an average of 5.6 hours to generate maintainable runnable systems, including a real-world ticket-booking application of approximately 10K lines of code. △ Less

Submitted 9 August, 2026; v1 submitted 14 February, 2026; originally announced February 2026.

Comments: This work is accepted at issta'26 (SIGSOFT International Symposium on Software Testing and Analysis)

WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements

Authors: Xiwen Teoh, Yun Lin, Duc-Minh Nguyen, Ruofei Ren, Wenjie Zhang, Jin Song Dong

Abstract: Visual language model (VLM) agents show great promise in automating end-to-end (E2E) web testing against requirements in natural language. However, the probabilistic nature of language models can have inherent hallucinations. Therefore, given a detected inconsistency between the requirement and the web application, it is hard to distinguish whether it stems from the hallucination or a real applica… ▽ More Visual language model (VLM) agents show great promise in automating end-to-end (E2E) web testing against requirements in natural language. However, the probabilistic nature of language models can have inherent hallucinations. Therefore, given a detected inconsistency between the requirement and the web application, it is hard to distinguish whether it stems from the hallucination or a real application bug. Addressing this issue presents two core technical challenges: the implicit oracle inference challenge, where the agent must act as its own oracle to implicitly decide if the application's behavior is correct without guidance, and the probabilistic inference challenge, where an LLM's inconsistent reasoning undermines its trustworthiness as an oracle. Existing LLM-based approaches fail to capture such implicit oracles, either by treating any page navigation that doesn't crash as a success, or by checking each state in isolation, thus missing bugs dependent on context from prior steps. We introduce WebTestPilot, an LLM-based agent designed to address these challenges. WebTestPilot uses (1) a symbolization layer which detects and symbolizes critical GUI elements on the web application into symbols (i.e., variables) and (2) translates natural language specification into a sequence of steps, each of which is equipped with inferred pre- and post-conditions over the symbols as an oracle. This oracle captures data, temporal, and causal dependencies, enabling the validation of implicit requirements. To advance research in this area, we build a benchmark of bug-injected web apps for evaluating NL-to-E2E testing. The results show that WebTestPilot achieves a task completion rate of 99%, with 96% precision and 96% recall in bug detection, outperforming the best baseline (+70 precision, +27 recall). The agent generalizes across diverse natural language inputs and model scales. △ Less

Submitted 23 April, 2026; v1 submitted 12 February, 2026; originally announced February 2026.

Beyond the Black Box: A Survey on the Theory and Mechanism of Large Language Models

Authors: Zeyu Gan, Ruifeng Ren, Wei Yao, Xiaolin Hu, Gengze Xu, Chen Qian, Huayi Tang, Zixuan Gong, Xinhao Yao, Pengwei Tang, Zhenxing Dou, Yong Liu

Abstract: The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasingly impact modern society. However, a critical paradox persists within the current field: despite the empirical efficacy, our theoretical understanding of LLMs remains disproportionately nascent, forcing these systems t… ▽ More The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasingly impact modern society. However, a critical paradox persists within the current field: despite the empirical efficacy, our theoretical understanding of LLMs remains disproportionately nascent, forcing these systems to be treated largely as ``black boxes''. To address this theoretical fragmentation, this survey proposes a unified lifecycle-based taxonomy that organizes the research landscape into six distinct stages: Data Preparation, Model Preparation, Training, Alignment, Inference, and Evaluation. Within this framework, we provide a systematic review of the foundational theories and internal mechanisms driving LLM performance. Specifically, we analyze core theoretical issues such as the mathematical justification for data mixtures, the representational limits of various architectures, and the optimization dynamics of alignment algorithms. Moving beyond current best practices, we identify critical frontier challenges, including the theoretical limits of synthetic data self-improvement, the mathematical bounds of safety guarantees, and the mechanistic origins of emergent intelligence. By connecting empirical observations with rigorous scientific inquiry, this work provides a structured roadmap for transitioning LLM development from engineering heuristics toward a principled scientific discipline. △ Less

Submitted 12 March, 2026; v1 submitted 6 January, 2026; originally announced January 2026.

DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions

Authors: Xiaoyu Lin, Aniket Ghorpade, Hansheng Zhu, Justin Qiu, Dea Rrozhani, Monica Lama, Mick Yang, Zixuan Bian, Ruohan Ren, Alan B. Hong, Jiatao Gu, Chris Callison-Burch

Abstract: With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limitation of current training datasets is their reliance on sparse annotations mined from the Internet or entered via manual typing that capture only a fraction of an image's visual content. Dense annotations are more valuab… ▽ More With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limitation of current training datasets is their reliance on sparse annotations mined from the Internet or entered via manual typing that capture only a fraction of an image's visual content. Dense annotations are more valuable but remain scarce. Traditional text-based annotation pipelines are poorly suited for creating dense annotations: typing limits expressiveness, slows annotation speed, and underrepresents nuanced visual features, especially in specialized areas such as multicultural imagery and 3D asset annotation. In this paper, we present DenseAnnotate, an audio-driven online annotation platform that enables efficient creation of dense, fine-grained annotations for images and 3D assets. Annotators narrate observations aloud while synchronously linking spoken phrases to image regions or 3D scene parts. Our platform incorporates speech-to-text transcription and region-of-attention marking. To demonstrate the effectiveness of DenseAnnotate, we conducted case studies involving over 1,000 annotators across two domains: culturally diverse images and 3D scenes. We curate a human-annotated multi-modal dataset of 3,531 images, 898 3D scenes, and 7,460 3D objects, with audio-aligned dense annotations in 20 languages, including 8,746 image captions, 2,000 scene captions, and 19,000 object captions. Models trained on this dataset exhibit improvements of 5% in multilingual, 47% in cultural alignment, and 54% in 3D spatial capabilities. Our results show that our platform offers a feasible approach for future vision-language research and can be applied to various tasks and diverse types of data. △ Less

Submitted 15 November, 2025; originally announced November 2025.

Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture

Authors: Tianhao Fu, Xinxin Xu, Weichen Xu, Jue Chen, Ruilong Ren, Bowen Deng, Xinyu Zhao, Jian Cao, Xixin Cao

Abstract: Market making (MM) through Reinforcement Learning (RL) has attracted significant attention in financial trading. With the development of Large Language Models (LLMs), more and more attempts are being made to apply LLMs to financial areas. A simple, direct application of LLM as an agent shows significant performance. Such methods are hindered by their slow inference speed, while most of the current… ▽ More Market making (MM) through Reinforcement Learning (RL) has attracted significant attention in financial trading. With the development of Large Language Models (LLMs), more and more attempts are being made to apply LLMs to financial areas. A simple, direct application of LLM as an agent shows significant performance. Such methods are hindered by their slow inference speed, while most of the current research has not studied LLM distillation for this specific task. To address this, we first propose the normalized fluorescent probe to study the mechanism of the LLM's feature. Based on the observation found by our investigation, we propose Cooperative Market Making (CMM), a novel framework that decouples LLM features across three orthogonal dimensions: layer, task, and data. Various student models collaboratively learn simple LLM features along with different dimensions, with each model responsible for a distinct feature to achieve knowledge distillation. Furthermore, CMM introduces an Hájek-MoE to integrate the output of the student models by investigating the contribution of different models in a kernel function-generated common feature space. Extensive experimental results on four real-world market datasets demonstrate the superiority of CMM over the current distillation method and RL-based market-making strategies. △ Less

Submitted 29 January, 2026; v1 submitted 10 November, 2025; originally announced November 2025.

Comments: accepted by AAAI2026

A Hybrid Deep Learning based Carbon Price Forecasting Framework with Structural Breakpoints Detection and Signal Denoising

Authors: Runsheng Ren, Jing Li, Yanxiu Li, Shixun Huang, Jun Shen, Wanqing Li, John Le, Sheng Wang

Abstract: Accurately forecasting carbon prices is essential for informed energy market decision-making, guiding sustainable energy planning, and supporting effective decarbonization strategies. However, it remains challenging due to structural breaks and high-frequency noise caused by frequent policy interventions and market shocks. Existing studies, including the most recent baseline approaches, have attem… ▽ More Accurately forecasting carbon prices is essential for informed energy market decision-making, guiding sustainable energy planning, and supporting effective decarbonization strategies. However, it remains challenging due to structural breaks and high-frequency noise caused by frequent policy interventions and market shocks. Existing studies, including the most recent baseline approaches, have attempted to incorporate breakpoints but often treat denoising and modeling as separate processes and lack systematic evaluation across advanced deep learning architectures, limiting the robustness and the generalization capability. To address these gaps, this paper proposes a comprehensive hybrid framework that integrates structural break detection (Bai-Perron, ICSS, and PELT algorithms), wavelet signal denoising, and three state-of-the-art deep learning models (LSTM, GRU, and TCN). Using European Union Allowance (EUA) spot prices from 2007 to 2024 and exogenous features such as energy prices and policy indicators, the framework constructs univariate and multivariate datasets for comparative evaluation. Experimental results demonstrate that our proposed PELT-WT-TCN achieves the highest prediction accuracy, reducing forecasting errors by 22.35% in RMSE and 18.63% in MAE compared to the state-of-the-art baseline model (Breakpoints with Wavelet and LSTM), and by 70.55% in RMSE and 74.42% in MAE compared to the original LSTM without decomposition from the same baseline study. These findings underscore the value of integrating structural awareness and multiscale decomposition into deep learning architectures to enhance accuracy and interpretability in carbon price forecasting and other nonstationary financial time series. △ Less

Submitted 20 November, 2025; v1 submitted 7 November, 2025; originally announced November 2025.

Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle

Authors: Ruifeng Ren, Sheng Ouyang, Huayi Tang, Yong Liu

Abstract: Attention-based Transformers have demonstrated strong adaptability across a wide range of tasks and have become the backbone of modern Large Language Models (LLMs). However, their underlying mechanisms remain open for further exploration. The energy-based perspective has long provided a valuable principle for understanding neural computation. In this paper, we revisit the principle of energy as a… ▽ More Attention-based Transformers have demonstrated strong adaptability across a wide range of tasks and have become the backbone of modern Large Language Models (LLMs). However, their underlying mechanisms remain open for further exploration. The energy-based perspective has long provided a valuable principle for understanding neural computation. In this paper, we revisit the principle of energy as a lens to understand attention-based Transformer models. We present a unified energy-based framework which is composed of three key components: the local energy $E_i$, the global energy $F$, and the employed optimization algorithms. We show that different attention forms including unnormalized linear attention, gated linear attention and standard softmax attention can be induced by choosing their corresponding recipes within this framework. Building on this framework, we propose energy-based modifications of attention structures. Inspired by classical gradient descent (GD) algorithms, we extend the original attention formulation based on standard GD to the momentum-based GD, Nesterov Accelerated Gradient (NAG), and Newton's method, each inducing a corresponding new attention structure. Our experiments provide preliminary support for the potential of the energy-based framework for designing attention mechanisms. △ Less

Submitted 12 January, 2026; v1 submitted 2 November, 2025; originally announced November 2025.

Remote Labor Index: Measuring AI Automation of Remote Work

Authors: Mantas Mazeika, Alice Gatti, Cristina Menghini, Udari Madhushani Sehwag, Shivam Singhal, Yury Orlovskiy, Steven Basart, Manasi Sharma, Denis Peskoff, Elaine Lau, Jaehyuk Lim, Lachlan Carroll, Alice Blair, Vinaya Sivakumar, Sumana Basu, Brad Kenstler, Yuntao Ma, Julian Michael, Xiaoke Li, Oliver Ingebretsen, Aditya Mehta, Jean Mottola, John Teichmann, Kevin Yu, Zaina Shaik , et al. (22 additional authors not shown)

Abstract: AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To measure this, we introduce the Remote Labor Index (RLI), a broadly multi-sector benchmark comprising real-world, economically valuable projects designed to evaluate end-to-end agent performance in practical settings. AI age… ▽ More AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To measure this, we introduce the Remote Labor Index (RLI), a broadly multi-sector benchmark comprising real-world, economically valuable projects designed to evaluate end-to-end agent performance in practical settings. AI agents perform near the floor on RLI, with the highest-performing agent achieving an automation rate of 2.5%. These results help ground discussions of AI automation in empirical evidence, setting a common basis for tracking AI impacts and enabling stakeholders to proactively navigate AI-driven labor automation. △ Less

Submitted 30 October, 2025; originally announced October 2025.

Comments: Website: https://www.remotelabor.ai

TeleEgo: Benchmarking Egocentric AI Assistants in the Wild

Authors: Jiaqi Yan, Ruilong Ren, Jingren Liu, Shuning Xu, Ling Wang, Yiheng Wang, Xinlin Zhong, Yun Wang, Long Zhang, Xiangyu Chen, Changzhi Sun, Jixiang Luo, Dell Zhang, Hao Sun, Chi Zhang, Xuelong Li

Abstract: Egocentric AI assistants in real-world settings must process multi-modal inputs (video, audio, text), respond in real time, and retain evolving long-term memory. However, existing benchmarks typically evaluate these abilities in isolation, lack realistic streaming scenarios, or support only short-term tasks. We introduce \textbf{TeleEgo}, a long-duration, streaming, omni-modal benchmark for evalua… ▽ More Egocentric AI assistants in real-world settings must process multi-modal inputs (video, audio, text), respond in real time, and retain evolving long-term memory. However, existing benchmarks typically evaluate these abilities in isolation, lack realistic streaming scenarios, or support only short-term tasks. We introduce \textbf{TeleEgo}, a long-duration, streaming, omni-modal benchmark for evaluating egocentric AI assistants in realistic daily contexts. The dataset features over 14 hours per participant of synchronized egocentric video, audio, and text across four domains: work \& study, lifestyle \& routines, social activities, and outings \& culture. All data is aligned on a unified global timeline and includes high-quality visual narrations and speech transcripts, curated through human refinement.TeleEgo defines 12 diagnostic subtasks across three core capabilities: Memory (recalling past events), Understanding (interpreting the current moment), and Cross-Memory Reasoning (linking distant events). It contains 3,291 human-verified QA items spanning multiple question formats (single-choice, binary, multi-choice, and open-ended), evaluated strictly in a streaming setting. We propose Real-Time Accuracy (RTA) to jointly capture correctness and responsiveness under tight decision windows, and Memory Persistence Time (MPT) as a forward-looking metric for long-term retention in continuous streams. In this work, we report RTA results for current models and release TeleEgo, together with an MPT evaluation framework, as a realistic and extensible benchmark for future egocentric assistants with stronger streaming memory, enabling systematic study of both real-time behavior and long-horizon memory. △ Less

Submitted 10 December, 2025; v1 submitted 27 October, 2025; originally announced October 2025.

A Multi-Store Privacy Measurement of Virtual Reality App Ecosystem

Authors: Chuan Yan, Zeng Li, Kunlin Cai, Liuhuo Wan, Ruomai Ren, Yiran Shen, Guangdong Bai

Abstract: Virtual Reality (VR) has gained increasing traction among various domains in recent years, with major companies such as Meta, Pico, and Microsoft launching their application stores to support third-party developers in releasing their applications (or simply apps). These apps offer rich functionality but inherently collect privacy-sensitive data, such as user biometrics, behaviors, and the surround… ▽ More Virtual Reality (VR) has gained increasing traction among various domains in recent years, with major companies such as Meta, Pico, and Microsoft launching their application stores to support third-party developers in releasing their applications (or simply apps). These apps offer rich functionality but inherently collect privacy-sensitive data, such as user biometrics, behaviors, and the surrounding environment. Nevertheless, there is still a lack of domain-specific regulations to govern the data handling of VR apps, resulting in significant variations in their privacy practices among app stores. In this work, we present the first comprehensive multi-store study of privacy practices in the current VR app ecosystem, covering a large-scale dataset involving 6,565 apps collected from five major app stores. We assess both declarative and behavioral privacy practices of VR apps, using a multi-faceted approach based on natural language processing, reverse engineering, and static analysis. Our assessment reveals significant privacy compliance issues across all stores, underscoring the premature status of privacy protection in this rapidly growing ecosystem. For instance, one third of apps fail to declare their use of sensitive data, and 21.5\% of apps neglect to provide valid privacy policies. Our work sheds light on the status quo of privacy protection within the VR app ecosystem for the first time. Our findings should raise an alert to VR app developers and users, and encourage store operators to implement stringent regulations on privacy compliance among VR apps. △ Less

Submitted 27 October, 2025; originally announced October 2025.

Comments: 16 pages

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards

Authors: Jiajun Fan, Roger Ren, Jingyuan Li, Rahul Pandey, Prashanth Gurunath Shivakumar, Ivan Bulyko, Ankur Gandhe, Ge Liu, Yile Gu

Abstract: The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inference, a phenomenon we term test-time inverse scaling, where longer reasoning chains yield progressively worse results. We demonstrate that this stems not from fundamental limitations of reasoning itself, but from inadequat… ▽ More The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inference, a phenomenon we term test-time inverse scaling, where longer reasoning chains yield progressively worse results. We demonstrate that this stems not from fundamental limitations of reasoning itself, but from inadequate training: models without proper guidance for the reasoning process produce hallucinatory, inconsistent reasoning that accumulates errors over longer chains. To address these challenges, we introduce CESAR (Consistent, Effective, and Scalable Audio Reasoners), shifting from outcome verification to rewarding the reasoning process. Our online reinforcement learning framework employs Group Relative Policy Optimization with a multi-faceted reward suite that incentivizes not only correctness and format but also consistency, structured analytical patterns, causal reasoning, domain-knowledge integration, and calibrated reasoning depth. CESAR resolves test-time inverse scaling, transforming reasoning from detriments into gains while revealing model-specific ``reasoning sweet spots", where performance peaks during test-time scaling. We achieve state-of-the-art results on MMAU Test-mini, substantially outperforming Gemini 2.5 Pro and GPT-4o Audio, and near-human-level performance on MMSU reasoning tasks. Through AI-as-judge evaluations and qualitative comparisons, we provide both quantitative and qualitative validation of our improved reasoning quality. Importantly, enhanced reasoning creates synergistic effects, simultaneously improving multimodal reasoning and perception capabilities. Overall, CESAR establishes a principled method for developing robust and scalable reasoning in Audio LLMs. △ Less

Submitted 23 October, 2025; originally announced October 2025.

Comments: 49 pages

Collective Communication for 100k+ GPUs

Authors: Min Si, Pavan Balaji, Yongzhou Chen, Ching-Hsiang Chu, Adi Gangidi, Saif Hasan, Subodh Iyengar, Dan Johnson, Bingzhe Liu, Regina Ren, Deep Shah, Ashmitha Jeevaraj Shetty, Greg Steinbrecher, Yulun Wang, Bruce Wu, Xinfeng Xie, Jingyi Yang, Mingran Yang, Kenny Yu, Minlan Yu, Cen Zhao, Wes Bland, Denis Boyda, Suman Gumudavelli, Prashanth Kannan , et al. (14 additional authors not shown)

Abstract: The increasing scale of large language models (LLMs) necessitates highly efficient collective communication frameworks, particularly as training workloads extend to hundreds of thousands of GPUs. Traditional communication methods face significant throughput and latency limitations at this scale, hindering both the development and deployment of state-of-the-art models. This paper presents the NCCLX… ▽ More The increasing scale of large language models (LLMs) necessitates highly efficient collective communication frameworks, particularly as training workloads extend to hundreds of thousands of GPUs. Traditional communication methods face significant throughput and latency limitations at this scale, hindering both the development and deployment of state-of-the-art models. This paper presents the NCCLX collective communication framework, developed at Meta, engineered to optimize performance across the full LLM lifecycle, from the synchronous demands of large-scale training to the low-latency requirements of inference. The framework is designed to support complex workloads on clusters exceeding 100,000 GPUs, ensuring reliable, high-throughput, and low-latency data exchange. Empirical evaluation on the Llama4 model demonstrates substantial improvements in communication efficiency. This research contributes a robust solution for enabling the next generation of LLMs to operate at unprecedented scales. △ Less

Submitted 9 January, 2026; v1 submitted 22 October, 2025; originally announced October 2025.

ACM Class: C.2.4; I.2

STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning

Authors: Chenghao Wu, Ruiyang Ren, Junjie Zhang, Ruirui Wang, Zhongrui Ma, Qi Ye, Wayne Xin Zhao

Abstract: While modern recommender systems are instrumental in navigating information abundance, they remain fundamentally limited by static user modeling and reactive decision-making paradigms. Current large language model (LLM)-based agents inherit these shortcomings through their overreliance on heuristic pattern matching, yielding recommendations prone to shallow correlation bias, limited causal inferen… ▽ More While modern recommender systems are instrumental in navigating information abundance, they remain fundamentally limited by static user modeling and reactive decision-making paradigms. Current large language model (LLM)-based agents inherit these shortcomings through their overreliance on heuristic pattern matching, yielding recommendations prone to shallow correlation bias, limited causal inference, and brittleness in sparse-data scenarios. We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities. Each user is modeled as an agent with parallel cognitions: fast response for immediate interactions and slow reasoning that performs chain-of-thought rationales. To cultivate intrinsic slow thinking, we develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping. This hybrid approach scaffolds agents in acquiring foundational capabilities (preference summarization, rationale generation) while enabling dynamic policy adaptation through simulated feedback loops. Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines, despite using only 0.4% of the full training data. △ Less

Submitted 26 August, 2025; originally announced August 2025.

Journal ref: Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025)

HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing

Authors: Zixuan Bian, Ruohan Ren, Yue Yang, Chris Callison-Burch

Abstract: 3D scene generation plays a crucial role in gaming, artistic creation, virtual reality, and many other domains. However, current 3D scene design still relies heavily on extensive manual effort from creators, and existing automated methods struggle to generate open-domain scenes or support flexible editing. To address those challenges, we introduce HOLODECK 2.0, an advanced vision-language-guided f… ▽ More 3D scene generation plays a crucial role in gaming, artistic creation, virtual reality, and many other domains. However, current 3D scene design still relies heavily on extensive manual effort from creators, and existing automated methods struggle to generate open-domain scenes or support flexible editing. To address those challenges, we introduce HOLODECK 2.0, an advanced vision-language-guided framework for 3D world generation with support for interactive scene editing based on human feedback. HOLODECK 2.0 can generate diverse and stylistically rich 3D scenes (e.g., realistic, cartoon, anime, and cyberpunk styles) that exhibit high semantic fidelity to fine-grained input descriptions, suitable for both indoor and open-domain environments. HOLODECK 2.0 leverages vision-language models (VLMs) to identify and parse the objects required in a scene and generates corresponding high-quality assets via state-of-the-art 3D generative models. Then, HOLODECK 2.0 iteratively applies spatial constraints derived from the VLMs to achieve semantically coherent and physically plausible layouts. Both human and model evaluations demonstrate that HOLODECK 2.0 effectively generates high-quality scenes closely aligned with detailed textual descriptions, consistently outperforming baselines across indoor and open-domain scenarios. Additionally, HOLODECK 2.0 provides editing capabilities that flexibly adapt to human feedback, supporting layout refinement and style-consistent object edits. Finally, we present a practical application of HOLODECK 2.0 in procedural game modeling to generate visually rich and immersive environments that can boost efficiency in game design Code is available at https://github.com/bzx20/Holodeck2.0. △ Less

Submitted 27 July, 2026; v1 submitted 7 August, 2025; originally announced August 2025.

BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation

Authors: Yuhao Wang, Ruiyang Ren, Yucheng Wang, Jing Liu, Wayne Xin Zhao, Hua Wu, Haifeng Wang

Abstract: With the rapid advancement of large language models (LLMs), retrieval-augmented generation (RAG) has emerged as a critical approach to supplement the inherent knowledge limitations of LLMs. However, due to the typically large volume of retrieved information, RAG tends to operate with long context lengths. From the perspective of entropy engineering, we identify unconstrained entropy growth and att… ▽ More With the rapid advancement of large language models (LLMs), retrieval-augmented generation (RAG) has emerged as a critical approach to supplement the inherent knowledge limitations of LLMs. However, due to the typically large volume of retrieved information, RAG tends to operate with long context lengths. From the perspective of entropy engineering, we identify unconstrained entropy growth and attention dilution due to long retrieval context as significant factors affecting RAG performance. In this paper, we propose the balanced entropy-engineered RAG (BEE-RAG) framework, which improves the adaptability of RAG systems to varying context lengths through the principle of entropy invariance. By leveraging balanced context entropy to reformulate attention dynamics, BEE-RAG separates attention sensitivity from context length, ensuring a stable entropy level. Building upon this, we introduce a zero-shot inference strategy for multi-importance estimation and a parameter-efficient adaptive fine-tuning mechanism to obtain the optimal balancing factor for different settings. Extensive experiments across multiple RAG tasks demonstrate the effectiveness of BEE-RAG. △ Less

Submitted 10 November, 2025; v1 submitted 7 August, 2025; originally announced August 2025.

The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach

Authors: Rui Ren

Abstract: In real-world scenarios, due to the highly decoupled and flexible nature of microservices, it poses greater challenges to system reliability. The more frequent occurrence of incidents has created a demand for Root Cause Analysis(RCA) methods that enable rapid identification and recovery of incidents. Large language model (LLM) provides a new path for quickly locating and recovering from incidents… ▽ More In real-world scenarios, due to the highly decoupled and flexible nature of microservices, it poses greater challenges to system reliability. The more frequent occurrence of incidents has created a demand for Root Cause Analysis(RCA) methods that enable rapid identification and recovery of incidents. Large language model (LLM) provides a new path for quickly locating and recovering from incidents by leveraging their powerful generalization ability combined with expert experience. Current LLM for RCA frameworks are based on ideas like ReAct and Chain-of-Thought, but the hallucination of LLM and the propagation nature of anomalies often lead to incorrect localization results. Moreover, the massive amount of anomalous information generated in large, complex systems presents a huge challenge for the context window length of LLMs. To address these challenges, we propose KnowledgeMind, an innovative LLM multi-agent system based on Monte Carlo Tree Search and a knowledge base reward mechanism for standardized service-by-service reasoning. Compared to State-Of-The-Art(SOTA) LLM for RCA methods, our service-by-service exploration approach significantly reduces the burden on the maximum context window length, requiring only one-tenth of its size. Additionally, by incorporating a rule-based real-time reward mechanism, our method effectively mitigates hallucinations during the inference process. Compared to the SOTA LLM for RCA framework, our method achieves a 49.29% to 128.35% improvement in root cause localization accuracy. △ Less

Submitted 30 July, 2025; originally announced July 2025.

Security study based on the Chatgptplugin system: ldentifying Security Vulnerabilities

Authors: Ruomai Ren

Abstract: Plugin systems are a class of external programmes that provide users with a wide range of functionality, and while they enhance the user experience, their security is always a challenge. Especially due to the diversity and complexity of developers, many plugin systems lack adequate regulation. As ChatGPT has become a popular large-scale language modelling platform, its plugin system is also gradua… ▽ More Plugin systems are a class of external programmes that provide users with a wide range of functionality, and while they enhance the user experience, their security is always a challenge. Especially due to the diversity and complexity of developers, many plugin systems lack adequate regulation. As ChatGPT has become a popular large-scale language modelling platform, its plugin system is also gradually developing, and the open platform provides creators with the opportunity to upload plugins covering a wide range of application scenarios. However, current research and discussions mostly focus on the security issues of the ChatGPT model itself, while ignoring the possible security risks posed by the plugin system. This study aims to analyse the security of plugins in the ChatGPT plugin shop, reveal its major security vulnerabilities, and propose corresponding improvements. △ Less

Submitted 16 August, 2025; v1 submitted 21 July, 2025; originally announced July 2025.

Comments: Master's thesis

Infinite Video Understanding

Authors: Dell Zhang, Xiangyu Chen, Jixiang Luo, Mengxi Jia, Changzhi Sun, Ruilong Ren, Jingren Liu, Hao Sun, Xuelong Li

Abstract: The rapid advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have ushered in remarkable progress in video understanding. However, a fundamental challenge persists: effectively processing and comprehending video content that extends beyond minutes or hours. While recent efforts like Video-XL-2 have demonstrated novel architectural solutions for extreme efficiency,… ▽ More The rapid advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have ushered in remarkable progress in video understanding. However, a fundamental challenge persists: effectively processing and comprehending video content that extends beyond minutes or hours. While recent efforts like Video-XL-2 have demonstrated novel architectural solutions for extreme efficiency, and advancements in positional encoding such as HoPE and VideoRoPE++ aim to improve spatio-temporal understanding over extensive contexts, current state-of-the-art models still encounter significant computational and memory constraints when faced with the sheer volume of visual tokens from lengthy sequences. Furthermore, maintaining temporal coherence, tracking complex events, and preserving fine-grained details over extended periods remain formidable hurdles, despite progress in agentic reasoning systems like Deep Video Discovery. This position paper posits that a logical, albeit ambitious, next frontier for multimedia research is Infinite Video Understanding -- the capability for models to continuously process, understand, and reason about video data of arbitrary, potentially never-ending duration. We argue that framing Infinite Video Understanding as a blue-sky research objective provides a vital north star for the multimedia, and the wider AI, research communities, driving innovation in areas such as streaming architectures, persistent memory mechanisms, hierarchical and adaptive representations, event-centric reasoning, and novel evaluation paradigms. Drawing inspiration from recent work on long/ultra-long video understanding and several closely related fields, we outline the core challenges and key research directions towards achieving this transformative capability. △ Less

Submitted 23 July, 2025; v1 submitted 11 July, 2025; originally announced July 2025.

GUIPilot: A Consistency-based Mobile GUI Testing Approach for Detecting Application-specific Bugs

Authors: Ruofan Liu, Xiwen Teoh, Yun Lin, Guanjie Chen, Ruofei Ren, Denys Poshyvanyk, Jin Song Dong

Abstract: In this work, we propose GUIPilot, an approach for detecting inconsistencies between the mobile design and their implementations. The mobile design usually consists of design mock-ups that specify (1) the expected screen appearances (e.g., widget layouts, colors, and shapes) and (2) the expected screen behaviors, regarding how one screen can transition into another (e.g., labeled widgets with text… ▽ More In this work, we propose GUIPilot, an approach for detecting inconsistencies between the mobile design and their implementations. The mobile design usually consists of design mock-ups that specify (1) the expected screen appearances (e.g., widget layouts, colors, and shapes) and (2) the expected screen behaviors, regarding how one screen can transition into another (e.g., labeled widgets with textual description). Given a design mock-up and the implementation of its application, GUIPilot reports both their screen inconsistencies as well as process inconsistencies. On the one hand, GUIPilot detects the screen inconsistencies by abstracting every screen into a widget container where each widget is represented by its position, width, height, and type. By defining the partial order of widgets and the costs of replacing, inserting, and deleting widgets in a screen, we convert the screen-matching problem into an optimizable widget alignment problem. On the other hand, we translate the specified GUI transition into stepwise actions on the mobile screen (e.g., click, long-press, input text on some widgets). To this end, we propose a visual prompt for the vision-language model to infer widget-specific actions on the screen. By this means, we can validate the presence or absence of expected transitions in the implementation. Our extensive experiments on 80 mobile applications and 160 design mock-ups show that (1) GUIPilot can achieve 94.5% precision and 99.6% recall in detecting screen inconsistencies, outperforming the state-of-the-art approach, such as GVT, by 66.2% and 56.6% respectively, and (2) GUIPilot reports zero errors in detecting process inconsistencies. Furthermore, our industrial case study on applying GUIPilot on a trading mobile application shows that GUIPilot has detected nine application bugs, and all the bugs were confirmed by the original application experts. △ Less

Submitted 8 June, 2025; originally announced June 2025.

Retrieval-Augmented Generation Systems for Intellectual Property via Synthetic Multi-Angle Fine-tuning

Authors: Runtao Ren, Jian Ma, Jianxi Luo

Abstract: Retrieval-Augmented Generation (RAG) systems in the Intellectual Property (IP) field often struggle with diverse user queries, including colloquial expressions, spelling errors, and ambiguous terminology, leading to inaccurate retrieval and suboptimal responses. To address this challenge, we propose Multi-Angle Question Generation and Retrieval Fine-Tuning Method (MQG-RFM), a novel framework that… ▽ More Retrieval-Augmented Generation (RAG) systems in the Intellectual Property (IP) field often struggle with diverse user queries, including colloquial expressions, spelling errors, and ambiguous terminology, leading to inaccurate retrieval and suboptimal responses. To address this challenge, we propose Multi-Angle Question Generation and Retrieval Fine-Tuning Method (MQG-RFM), a novel framework that leverages large language models (LLMs) to simulate varied user inquiries and fine-tunes retrieval models to align semantically equivalent but linguistically diverse questions. Unlike complex architectural modifications, MQG-RFM adopts a lightweight Data-to-Tune paradigm, combining prompt-engineered query generation with hard negative mining to enhance retrieval robustness without costly infrastructure changes. Experimental results on a Taiwan patent Q&A dataset show 185.62% improvement in retrieval accuracy on the Patent Consultation dataset and 262.26% improvement on the Novel Patent Technology Report dataset, with 14.22% and 53.58% improvements in generation quality over the baselines, respectively. By bridging the gap between user intent and system comprehension through semantic-aware retrieval optimization, MQG-RFM offers a practical, scalable approach for rapid, cost-effective deployment among small and medium-sized agencies seeking reliable patent intelligence solutions. Additionally, our proposed method has already been adopted by ScholarMate, the largest professional research social networking platform in China, to support real-world development and deployment. A demo version of the instantiated is available at https://github.com/renruntao/patent_rag. △ Less

Submitted 31 May, 2025; originally announced June 2025.

Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation

Authors: Yuhao Wang, Ruiyang Ren, Yucheng Wang, Wayne Xin Zhao, Jing Liu, Hua Wu, Haifeng Wang

Abstract: Long-form question answering (LFQA) requires open-ended long-form responses that synthesize coherent, factually grounded content from multi-source evidence. This makes reinforcement learning (RL) reward design critical. The reward must be verifiable for faithful grounding and stable optimization. However, many standard rewards assume a unique target with an exact-match notion of correctness, which… ▽ More Long-form question answering (LFQA) requires open-ended long-form responses that synthesize coherent, factually grounded content from multi-source evidence. This makes reinforcement learning (RL) reward design critical. The reward must be verifiable for faithful grounding and stable optimization. However, many standard rewards assume a unique target with an exact-match notion of correctness, which fits short-form QA and math but breaks in LFQA. As a result, current RAG systems still lack verifiable reward mechanisms, yielding unstable feedback signals and suboptimal optimization outcomes. We propose RioRAG, a framework for reinforced verifiable informativeness optimization. First, it defines informativeness as a measurable and externally verifiable objective for RL. Second, RioRAG uses nugget-centric verification with cross-source checks to enable self-evolution of smaller LLMs and to provide denser, action-discriminative rewards that mitigate reward sparsity and stabilize optimization. This formulation avoids handcrafted supervision for the policy model and strong teacher-model distillation, relying instead on externally verifiable feedback. Experiments on LongFact and RAGChecker show that RioRAG achieves higher factual recall and faithfulness, establishing verifiable reward modeling as a foundation for trustworthy long-form RAG. Our codes are available at https://github.com/RUCAIBox/RioRAG. △ Less

Submitted 7 May, 2026; v1 submitted 27 May, 2025; originally announced May 2025.

On Path to Multimodal Historical Reasoning: HistBench and HistAgent

Authors: Jiahao Qiu, Fulian Xiao, Yimin Wang, Yuchen Mao, Yijia Chen, Xinzhe Juan, Shu Zhang, Siran Wang, Xuan Qi, Tongcheng Zhang, Zixin Yao, Jiacheng Guo, Yifu Lu, Charles Argon, Jundi Cui, Daixin Chen, Junran Zhou, Shuyao Zhou, Zhanpeng Zhou, Ling Yang, Shilong Liu, Hongru Wang, Kaixuan Huang, Xun Jiang, Yuming Cao , et al. (74 additional authors not shown)

Abstract: Recent advances in large language models (LLMs) have led to remarkable progress across domains, yet their capabilities in the humanities, particularly history, remain underexplored. Historical reasoning poses unique challenges for AI, involving multimodal source interpretation, temporal inference, and cross-linguistic analysis. While general-purpose agents perform well on many existing benchmarks,… ▽ More Recent advances in large language models (LLMs) have led to remarkable progress across domains, yet their capabilities in the humanities, particularly history, remain underexplored. Historical reasoning poses unique challenges for AI, involving multimodal source interpretation, temporal inference, and cross-linguistic analysis. While general-purpose agents perform well on many existing benchmarks, they lack the domain-specific expertise required to engage with historical materials and questions. To address this gap, we introduce HistBench, a new benchmark of 414 high-quality questions designed to evaluate AI's capacity for historical reasoning and authored by more than 40 expert contributors. The tasks span a wide range of historical problems-from factual retrieval based on primary sources to interpretive analysis of manuscripts and images, to interdisciplinary challenges involving archaeology, linguistics, or cultural history. Furthermore, the benchmark dataset spans 29 ancient and modern languages and covers a wide range of historical periods and world regions. Finding the poor performance of LLMs and other agents on HistBench, we further present HistAgent, a history-specific agent equipped with carefully designed tools for OCR, translation, archival search, and image understanding in History. On HistBench, HistAgent based on GPT-4o achieves an accuracy of 27.54% pass@1 and 36.47% pass@2, significantly outperforming LLMs with online search and generalist agents, including GPT-4o (18.60%), DeepSeek-R1(14.49%) and Open Deep Research-smolagents(20.29% pass@1 and 25.12% pass@2). These results highlight the limitations of existing LLMs and generalist agents and demonstrate the advantages of HistAgent for historical reasoning. △ Less

Submitted 19 June, 2025; v1 submitted 26 May, 2025; originally announced May 2025.

Comments: 17 pages, 7 figures

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

Authors: Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Wayne Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen

Abstract: Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical limitations that lack high-quality training trajectories or suffer from the distributional mismatches in simulated environments and prohibitive computational costs for… ▽ More Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical limitations that lack high-quality training trajectories or suffer from the distributional mismatches in simulated environments and prohibitive computational costs for real-world deployment. This paper introduces SimpleDeepSearcher, a lightweight yet effective framework that bridges this gap through strategic data engineering rather than complex training paradigms. Our approach synthesizes high-quality training data by simulating realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy that optimizes the diversity and quality of input and output side. Experiments on five benchmarks across diverse domains demonstrate that SFT on only 871 curated samples yields significant improvements over RL-based baselines. Our work establishes SFT as a viable pathway by systematically addressing the data-scarce bottleneck, offering practical insights for efficient deep search systems. Our code is available at https://github.com/RUCAIBox/SimpleDeepSearcher. △ Less

Submitted 8 October, 2025; v1 submitted 22 May, 2025; originally announced May 2025.

Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation

Authors: Yuhao Wang, Ruiyang Ren, Yucheng Wang, Wayne Xin Zhao, Jing Liu, Hua Wu, Haifeng Wang

Abstract: Considering the inherent limitations of parametric knowledge in large language models (LLMs), retrieval-augmented generation (RAG) is widely employed to expand their knowledge scope. Since RAG has shown promise in knowledge-intensive tasks like open-domain question answering, its broader application to complex tasks and intelligent assistants has further advanced its utility. Despite this progress… ▽ More Considering the inherent limitations of parametric knowledge in large language models (LLMs), retrieval-augmented generation (RAG) is widely employed to expand their knowledge scope. Since RAG has shown promise in knowledge-intensive tasks like open-domain question answering, its broader application to complex tasks and intelligent assistants has further advanced its utility. Despite this progress, the underlying knowledge utilization mechanisms of LLM-based RAG remain underexplored. In this paper, we present a systematic investigation of the intrinsic mechanisms by which LLMs integrate internal (parametric) and external (retrieved) knowledge in RAG scenarios. Specially, we employ knowledge stream analysis at the macroscopic level, and investigate the function of individual modules at the microscopic level. Drawing on knowledge streaming analyses, we decompose the knowledge utilization process into four distinct stages within LLM layers: knowledge refinement, knowledge elicitation, knowledge expression, and knowledge contestation. We further demonstrate that the relevance of passages guides the streaming of knowledge through these stages. At the module level, we introduce a new method, knowledge activation probability entropy (KAPE) for neuron identification associated with either internal or external knowledge. By selectively deactivating these neurons, we achieve targeted shifts in the LLM's reliance on one knowledge source over the other. Moreover, we discern complementary roles for multi-head attention and multi-layer perceptron layers during knowledge formation. These insights offer a foundation for improving interpretability and reliability in retrieval-augmented LLMs, paving the way for more robust and transparent generative solutions in knowledge-intensive domains. △ Less

Submitted 17 May, 2025; originally announced May 2025.

Comments: SIGIR 2025