Showing 1–50 of 758 results for author: Zheng, B

A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings

Authors: Hei Ting, Chan, Chenwei Wu, Xueshen Liu, Zesen Zhao, Boyuan Zheng, Luis Filipe Nakayama, Michael G. Morley, Liyue Shen, Jiasi Chen, Z. Morley Mao

Abstract: Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth is scarce, compute is limited, and clinical decision-making requires integrating heterogeneous modalities. We introduce a cloud--edge collaborative architecture that addresses these constraints: lightweight, domain-specific mode… ▽ More Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth is scarce, compute is limited, and clinical decision-making requires integrating heterogeneous modalities. We introduce a cloud--edge collaborative architecture that addresses these constraints: lightweight, domain-specific models on the edge transform raw medical data into compact structured outputs, while a cloud LLM synthesizes these outputs into clinical summaries. An LLM-based orchestrator dynamically selects diagnostic tools based on patient context, promoting comprehensive modality coverage without processing irrelevant inputs. We evaluate on 20 multimodal clinical cases spanning cardiac, obstetric, trauma, and screening scenarios under three simulated network profiles (500,kbps--5,Mbps). The hybrid system achieves 98--99% diagnostic tool recall with 92--96% precision, matches or exceeds cloud-only baselines on clinical accuracy, and maintains bandwidth-invariant latency (25--35,s) at 4--15x lower token cost. These results highlight the role of architectural design in enabling efficient multimodal integration and improving factual grounding compared to cloud-only approaches under deployment constraints. △ Less

Submitted 18 August, 2026; v1 submitted 12 August, 2026; originally announced August 2026.

Comments: 31 pages, 3 figures. In Proceedings of Machine Learning Research, Volume 340, 2026 (Machine Learning for Healthcare Conference)

MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning

Authors: Zirui Cheng, Xun Xu, Tiankai Chen, Fady Rezk, Bowen Zheng, Xiaodong Shi, Shijie Li, Kangkang Lu, Bharadwaj Veeravalli, Nancy F. Chen

Abstract: Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance is highly sensitive to the quality and coverage of the selected demonstrations. While unlabeled multi-modal data is abundant, it remains elusive how to exploit them for ICL. We propose MAG (MAnifold-Guided semi-supervised in-context demonstra- tio… ▽ More Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance is highly sensitive to the quality and coverage of the selected demonstrations. While unlabeled multi-modal data is abundant, it remains elusive how to exploit them for ICL. We propose MAG (MAnifold-Guided semi-supervised in-context demonstra- tion selection), an efficient framework that leverages unlabeled data to improve multi-modal ICL. MAG formulates demonstration selection as a semi-supervised propagation problem on a multi-modal graph and adopts a two-stage strategy: (i) relevance score propagation identifies a compact set of high-impact unlabeled samples for pseudo-labeling, reducing MLLM inference cost; (ii) multi-modal relevance is used to select the final demonstrations. We show that textual represen- tations are more effective for relevance propagation, while both visual and textual modalities are crucial for high-quality demonstration selection. Experiments on eight multi-modal benchmarks demonstrate that MAG consistently outperforms strong baselines in label-scarce regimes, achieving significant gains with a limited pseudo-labeling budget. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models

Authors: Yushi Ye, Xu Chen, Haoyun Jiang, Jinsong Lan, Haihong Tang, Bo Han, Ivor Tsang, Yanfeng Wang, Bo Zheng, Jiangchao Yao

Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding. We identify a rippl… ▽ More Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding. We identify a ripple effect in dLLM decoding: proactively committing a mid-entropy pivot position can induce a pronounced reduction in uncertainty across the remaining masked positions. This uncertainty reduction allows subsequent steps to unmask more tokens in parallel, thereby accelerating the overall decoding process. To exploit the ripple effect, we propose Ripple-Pivot Search (RPS), a novel training-free decoding method that seeks mid-entropy positions as promising candidate pivots (where to decode), and determines their token assignment that yields the greatest downstream benefit via lookahead evaluation (what to decode). Across 3 dLLMs and 4 reasoning and code-generation benchmarks, RPS achieves 4-10$\times$ wall-clock speedup over the standard decoder while preserving generation quality, and improves accuracy over the previous lookahead baseline by up to 5.49% while delivering higher throughput in most settings. When integrated with KV caching, RPS further achieves up to 18$\times$ wall-clock speedup over the standard decoder. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Persistent Recursive Worlds Enable Autonomous Software Evolution

Authors: Beichen Huang, Zhenyu Liang, Bowen Zheng, Ran Cheng

Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents softwa… ▽ More Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents software as a persistent recursive world: each local world is situated by an accepted version and a repository path, finite-lived agents propose local changes, recursive delegation moves work across paths, and only accepted consequences advance the persistent version history. We evaluate this organization across formation, continuation and redevelopment. Starting from a repository with no compiler implementation, Genesis used DeepSeek V4 Flash to build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US\$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated with GLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55--6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent. Project Website: https://genesis.evox.group/ △ Less

Submitted 16 August, 2026; v1 submitted 11 August, 2026; originally announced August 2026.

DREAM Technical Report

Authors: Bin Zhang, Bowen Zheng, Chao Yi, Chengyu Lai, Dian Chen, Dimin Wang, Gaoyang Guo, Jialin Zhu, Jian Wu, Jing Yu, Jiuning Lin, Lingqing Zhang, Lingyun Zheng, Mao Zhang, Mingming Pan, Ruiquan Lan, Shuai Zhong, Wen Chen, Wendong Zhang, Xiaodong Zhu, Xuan Chen, Xunke Xi, Yifan Lu, Yiheng Wang, Yue Zeng , et al. (52 additional authors not shown)

Abstract: Industrial recommender systems commonly use cascaded retrieval, ranking, and re-ranking pipelines. Although efficient, these pipelines fragment information and objectives across modules, rely on rigid rules, and have limited awareness of real-time intent, leaving session-level shifts among browsing, comparison, and purchase insufficiently addressed. We present DREAM (Developing Recommender Engine… ▽ More Industrial recommender systems commonly use cascaded retrieval, ranking, and re-ranking pipelines. Although efficient, these pipelines fragment information and objectives across modules, rely on rigid rules, and have limited awareness of real-time intent, leaving session-level shifts among browsing, comparison, and purchase insufficiently addressed. We present DREAM (Developing Recommender Engine with Agentic Methods), an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them. DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%. Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with safety guardrails. A Reward Dual Loop continuously optimizes both components by combining offline simulation for strategy-space exploration with online feedback for outcome calibration, forming a cycle of generation, execution, evaluation, and experience accumulation. Large-scale A/B tests on Taobao's homepage feed show that re-ranking control alone improves IPV by 2.06%, Core IPV by 2.39%, and GMV by 0.88%. Extending control to fine ranking raises these gains to 2.71%, 3.06%, and 1.31%, respectively, while consistently improving PV by more than 1%. These gains require neither replacement of pipeline models nor compromise of serving stability, supporting agentic meta-control as a viable paradigm for industrial recommendation. △ Less

Submitted 13 August, 2026; v1 submitted 10 August, 2026; originally announced August 2026.

Comments: Technical Report

EvoHIL: Self-Evolving Reward and Flow-Matched Policy Optimization for Robust Human-in-the-Loop Reinforcement Learning

Authors: Shuoqin Zhang, Tongtong Cheng, Xiru Gao, Jinzhuo Peng, Bin Zheng, Jiahao Tu, Ke Wang, Jia Pan, Zhe Hu, Kai Liu

Abstract: Human-in-the-loop reinforcement learning (HIL-RL) enables robots to learn contact-rich manipulation from limited real-world interaction, but deployment exposes three coupled limitations: static visual reward models fail under scene changes; independently sampled actions cause temporally inconsistent motion; and vision-based policies remain sensitive to appearance shifts. We present EvoHIL, a unifi… ▽ More Human-in-the-loop reinforcement learning (HIL-RL) enables robots to learn contact-rich manipulation from limited real-world interaction, but deployment exposes three coupled limitations: static visual reward models fail under scene changes; independently sampled actions cause temporally inconsistent motion; and vision-based policies remain sensitive to appearance shifts. We present EvoHIL, a unified framework that adapts the reward model, action generator, and visual do main within a staged human-in-the-loop learning process. First, self-evolving reward (SER) adapts the success classifier from human-confirmed positives and provisional weak negatives. Second, Action Flow Stabilization (AFS) generates temporally coherent action chunks through flow matching, grounding policy updates in executed action prefixes and demonstrated behavior. Third, retention-aware offline fine-tuning replays relit interaction data while anchoring the AFS actor-critic to prior behavior, adapting the visual domain without additional robot interaction. Across six manipulation tasks on Franka FR3 and SO-101 arms under a controlled lighting shift, EvoHIL improves task success, agreement with human-confirmation labels, motion smoothness, and completion time relative to human-in-the-loop and imitation baselines.Project page: https://anonymous4366.github.io/EvoHIL/ △ Less

Submitted 4 August, 2026; originally announced August 2026.

GROVE: Growing and Reasoning over Temporally Stratified Memory from Streaming Video Experience

Authors: Sitong Gong, Caixin Kang, Tianyu Yan, Guo Chen, Bo Zheng, Kaipeng Zhang, Yunzhi Zhuge, Xiang Ruan, Huchuan Lu, Yifei Huang

Abstract: A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown… ▽ More A wearable assistant should both answer questions about its visual history and recognize when that history is useful to the present situation. Existing video-memory systems primarily support question-conditioned recall, whereas proactive assistants typically use separate memory and control mechanisms. We introduce GROVE, a training-free framework that supports both behaviors with one memory grown causally from a continuous video stream. GROVE retains fine-grained perceptual evidence and incrementally consolidates it into time-stamped moments, coherent episodes, and recurring cross-day patterns. Each stratum is paired with a scale-native retrieval skill for locating an observation, replaying an activity, or traversing long-range regularities. Reactive QA and proactive assistance share this memory and access interface, differing in whether retrieval is initiated by a user query or the current situation. Across multiple benchmarks including the challenging MM-lifelong and EgoServe, GROVE achieves the best results among the compared methods. Controlled ablations show that the temporal strata and their access skills are complementary, with patterns providing the largest benefit when evidence spans multiple days. Code will be available at https://github.com/SitongGong/GROVE. △ Less

Submitted 5 August, 2026; v1 submitted 3 August, 2026; originally announced August 2026.

Multi-channel Uplift Policy Learning

Authors: Changjian Liu, Tianyu Wang, Xiaoxuan Deng, WenTao Zhu, Yuwei Xu, Jungqi Jin, Yong Gao, Chuan Yu, Jian Xu, Bo Zheng

Abstract: E-commerce platforms must allocate fixed marketing budgets across multiple channels to maximize business utility. However, standard predict-then-optimize (PTO) paradigms fail in this compositional space due to observational confounding and severe extrapolation. We formulate this challenge as a simplex-constrained uplift decision problem and propose ReAlloc, a fast-slow causal framework. Specifical… ▽ More E-commerce platforms must allocate fixed marketing budgets across multiple channels to maximize business utility. However, standard predict-then-optimize (PTO) paradigms fail in this compositional space due to observational confounding and severe extrapolation. We formulate this challenge as a simplex-constrained uplift decision problem and propose ReAlloc, a fast-slow causal framework. Specifically, an agile Orthogonal Teacher extracts unbiased local gradients from short-term logs, while an Explanation-Guided Student distills them into a structured marginal field over long-term horizons. This design enables support-aware, conservative decisions that capture cross-channel substitutions. Extensive simulations and large-scale online A/B tests on Taobao platform demonstrate that ReAlloc achieves simultaneous lifts in both pay order and income. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Group-Reflective Self-Distillation for Agentic Reinforcement Learning

Authors: Binbin Zheng, Zijun Xie, Guanqun Zhao, Enlei Gong, Xing Ma, Xiaoliang Fu, Zeyu Chen

Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recurring mistakes, and incidental choices entangled in the same outcome signal. Existing agentic self-distillation methods enrich sparse supervision with natural-language skills, but s… ▽ More Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recurring mistakes, and incidental choices entangled in the same outcome signal. Existing agentic self-distillation methods enrich sparse supervision with natural-language skills, but skills retrieved externally or extracted from a single trajectory by stronger models may mismatch current experience, exceed the policy's capability, or remain path-specific. We propose Group-Reflective Self-Distillation (GRSD), which derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts. For each prompt, the policy reflects on each verified trajectory in an on-policy group, and a stop-gradient snapshot contrasts the resulting reflections from successful and failed rollouts to construct group-level privileged guidance. Conditioned on this guidance, a self-teacher refines turn-level credit assignment by modulating outcome-based advantages while preserving the verifier-determined learning direction. Experiments across multiple agentic environments and model scales demonstrate that GRSD consistently outperforms competitive baselines and generalizes more effectively to unseen tasks. △ Less

Submitted 3 August, 2026; v1 submitted 30 July, 2026; originally announced July 2026.

LoopMemGR: From Behavior Logs to Evolving Memory for Generative Recommendation

Authors: Hui Qian, Changfa Wu, Chang Liu, Binbin Cao, Jian Wu, Yuliang Yan, Han Zhu, Bo Zheng

Abstract: Generative recommendation formulates next-item prediction as conditional autoregressive generation over discrete Semantic IDs, enabling end-to-end recommendation over large-scale item spaces. However, most existing methods follow a history-as-context paradigm that repeatedly reconstructs user preference from behavior history while discarding system-side recommendation decisions after each request.… ▽ More Generative recommendation formulates next-item prediction as conditional autoregressive generation over discrete Semantic IDs, enabling end-to-end recommendation over large-scale item spaces. However, most existing methods follow a history-as-context paradigm that repeatedly reconstructs user preference from behavior history while discarding system-side recommendation decisions after each request. This creates an asymmetric memory: the system remembers what the user has done, but not what it has previously recommended or learned from the resulting feedback. Consequently, useful preference-validation signals, potential negative evidence, and historical exploration information cannot be directly reused across requests. To address these limitations, we propose LoopMemGR, a closed-loop recommendation experience memory framework for generative recommendation. In addition to the conventional behavior log, LoopMemGR maintains a recommendation experience log that records past recommendation--feedback trajectories. It extracts request-relevant evidence through three complementary views: the recency view captures short-term interaction dynamics, the frequency view summarizes recurring recommendation patterns, and the global view distills transferable regularities shared across users. These signals are compressed into a fixed number of experience tokens to condition the generative backbone under a bounded input budget. Extensive experiments on an industrial Taobao dataset demonstrate the effectiveness of closed-loop experience accumulation and multi-view experience extraction. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Guess Where You Go: Generative Next Point-of-Interest Recommendation in Amap

Authors: Penglong Zhai, Bowen Zheng, Jie Li, Yifang Yuan, Yue Liu, Sicong Wang, Mingyang Yin, Tingting Hu, Shuaijun Guo, Fanyi Di, Xin Li

Abstract: Generative retrieval enables recommender systems to retrieve items by generating compact item identifiers, but scaling it to industrial scenarios remains challenging due to redundant or colliding token assignments and insufficient integration of heterogeneous item signals. These challenges are particularly critical for next Point-of-Interest (POI) recommendation, where models must represent struct… ▽ More Generative retrieval enables recommender systems to retrieve items by generating compact item identifiers, but scaling it to industrial scenarios remains challenging due to redundant or colliding token assignments and insufficient integration of heterogeneous item signals. These challenges are particularly critical for next Point-of-Interest (POI) recommendation, where models must represent structured spatial entities, capture sequential mobility patterns, and produce predictions consistent with real user behavior. We propose Gwhere, an end-to-end industrial framework that integrates semantic identifier (SID) generation with LLM-based generative next POI recommendation. Gwhere first learns discriminative POI SIDs through a contrastive residual-quantization tokenizer that aligns textual, visual, spatial, and collaborative signals. Based on these SIDs, Gwhere adapts LLMs to mobility scenarios via continued pretraining on enriched spatio-temporal corpora, supervised fine-tuning, and Exposure-Aware Kahneman-Tversky Optimization (EAKTO), a reinforcement learning objective for behavioral preference alignment. Experiments on public datasets and Amap's large-scale industrial dataset demonstrate the effectiveness of Gwhere. The system has been deployed in Amap's homepage service under high-concurrency and low-latency constraints. Long-term online A/B tests show improvements of 5.83% in P-CTR and 6.20% in U-CTR over the production baseline. The implementation is publicly available at https://github.com/alibaba/SimCIT. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Comments: 10 pages, 4 figures

SPARC: Sequence-aware Progressive Attribute Routing and Compression Framework for Generative Recommendation

Authors: Chang Liu, Changfa Wu, Hui Qian, Binbin Cao, Jian Wu, Yuliang Yan, Han Zhu, Bo Zheng

Abstract: Generative recommendation tokenizes items as discrete Semantic IDs (SIDs) and autoregressively generates target items from users' historical SID sequences. Although existing SIDs incorporate multimodal and structured information, they are typically statically assigned and independent of the current interaction context. In industrial scenarios, each behavior also contains heterogeneous attributes,… ▽ More Generative recommendation tokenizes items as discrete Semantic IDs (SIDs) and autoregressively generates target items from users' historical SID sequences. Although existing SIDs incorporate multimodal and structured information, they are typically statically assigned and independent of the current interaction context. In industrial scenarios, each behavior also contains heterogeneous attributes, such as category, brand, price, behavior type, and timestamp. Fully expanding these features greatly increases the input length, while directly compressing them into a single representation may prematurely discard context-relevant information. We propose \textbf{SPARC}, \uline{\textbf{S}}equence-aware \uline{\textbf{P}}rogressive \uline{\textbf{A}}ttribute \uline{\textbf{R}}outing and \uline{\textbf{C}}ompression Framework for Generative recommendation. SPARC first models the sequential dependencies of each field type to obtain context-aware field representations. It then routes the original, contextual, and identity representations of different fields into multiple slots to preserve complementary information under a fixed capacity. Finally, lightweight cross-item interaction integrates the intermediate tokens and compresses each historical item into a single token. Following the principle of contextualizing before compression, SPARC enriches user-history representations without increasing the input length of the generative backbone. Experiments on industrial Taobao and public Amazon datasets demonstrate that SPARC outperforms strong conventional and generative baselines. Further comparisons with static compression variants show that the improvement of SPARC comes from context-conditioned information retention rather than merely increasing the expressiveness of the compression module. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Unified Semantic Modeling Framework for Large-Scale Job Understanding at LinkedIn

Authors: Dan Xu, Baofen Zheng, Jianqiang Shen, Qi Xiao, Benjamin Hoan Le, Wen Pu, Saurabh Gupta, Ran Zhou, Neha Saraf, Alice Leung, Qianqi Shen, Liangjie Hong, Jingwei Wu, Wenjing Zhang

Abstract: Job understanding is critical to LinkedIn's mission of connecting talent with opportunity. This task involves transforming unstructured and noisy job postings into standardized or derived job attributes that power numerous LinkedIn products. However, building a scalable, cost-efficient, and high-performing job understanding system remains challenging. In this paper, we present a unified semantic m… ▽ More Job understanding is critical to LinkedIn's mission of connecting talent with opportunity. This task involves transforming unstructured and noisy job postings into standardized or derived job attributes that power numerous LinkedIn products. However, building a scalable, cost-efficient, and high-performing job understanding system remains challenging. In this paper, we present a unified semantic modeling framework powered by a small language model (SLM) to address the challenges. We begin by fine-tuning an open-source SLM using a suite of carefully curated synthetic tasks augmented with reasoning traces. These tasks jointly target taxonomy-guided classification and taxonomy-agnostic entity extraction. This allows the resulting model to acquire robust zero-shot generalization for job understanding in structured and unstructured contexts. Building upon this foundation, we introduce a multi-adapter architecture with attribute grouping to facilitate efficient task-specific adaptation while streamlining model management across diverse downstream attributes. Offline evaluations and online A/B tests demonstrate significant performance improvement while reducing operational complexity. Our work provides practical insights into building industry-scale text understanding systems. △ Less

Submitted 22 June, 2026; originally announced July 2026.

Strategy-Aware Parameter-Efficient Adaptation for LLM-based Auto-Bidding

Authors: Songyue Cai, Lianyu Wang, Shan Gu, Ziru Xu, Jian Xu, Xiaofeng Zhu, Bo Zheng

Abstract: Advertising bidding has evolved from manual strategies to auto-bidding systems better adapted for large-scale, dynamic auction environments. While recent advances in Large Language Models (LLMs) offer strong reasoning for auto-bidding, existing methods suffer from shallow trajectory-text interactions and require costly fine-tuning, hindering the efficient use of pretrained knowledge under diverse… ▽ More Advertising bidding has evolved from manual strategies to auto-bidding systems better adapted for large-scale, dynamic auction environments. While recent advances in Large Language Models (LLMs) offer strong reasoning for auto-bidding, existing methods suffer from shallow trajectory-text interactions and require costly fine-tuning, hindering the efficient use of pretrained knowledge under diverse constraints. To address these challenges, we propose SAGE, a novel Strategy-aware Auto-bidding framework Guided by LLMs for Efficient bidding. SAGE introduces a parameter-efficient multi-modal alignment framework for constrained auto-bidding with LLMs. Specifically, SAGE comprises three key components: (i) the position augmentation module adopts temporal-semantic positional embeddings to effectively capture the intrinsic dynamics and semantic structures; (ii) the text alignment module leverages gated cross-attention to align the embedding spaces of trajectory and text modalities, enabling effective multi-modal fusion while alleviating the computational overhead caused by long trajectories; (iii) the constraint-gated LoRA module employs constraints as routing signals, activating only a small subset of experts to adapt the behavior of a frozen LLM efficiently. Extensive experiments on large-scale auto-bidding benchmark demonstrate that SAGE consistently achieves superior performance while tuning less than 10% of the trainable parameters required by full fine-tuning. Ablation studies further validate the critical contribution of each component to the framework's overall performance. △ Less

Submitted 27 July, 2026; originally announced July 2026.

ClawRec: A Claw-Native Recommender System

Authors: Chenghao Wu, Kesha Ou, Xiaolei Wang, Bowen Zheng, Bingqian Li, Enze Liu, Wayne Xin Zhao, Weitao Li, Long Zhang, Sheng Chen, Ji-Rong Wen

Abstract: Recommender systems have become integral to navigating the modern digital ecosystem. Yet most deployed systems remain confined within single-platform boundaries, observing localized interaction traces and ranking items from isolated candidate spaces. This design is poorly suited to real-world tasks that unfold through searches, content consumption, and comparisons across multiple information sourc… ▽ More Recommender systems have become integral to navigating the modern digital ecosystem. Yet most deployed systems remain confined within single-platform boundaries, observing localized interaction traces and ranking items from isolated candidate spaces. This design is poorly suited to real-world tasks that unfold through searches, content consumption, and comparisons across multiple information sources. Claw-style personal agents, with persistent access to authorized cross-platform context, create an opportunity for recommendation to operate around the user rather than any single platform. In this paper, we introduce Claw-native recommender systems, a new paradigm that moves beyond platform-local ranking to produce unified, complementary recommendation slates spanning diverse sources and content forms. To instantiate this paradigm, we present ClawRec, the first recommender system designed to operate natively in this environment. ClawRec maintains an evidence-linked, temporally structured user state that connects cross-platform behaviors with cross-source recommendations. It organizes retrieval around functional source roles and selects candidates according to their marginal utility, producing non-redundant slates aligned with the user's active task. To enable rigorous evaluation, we introduce ClawRec-SimBench, a benchmark constructed from sequences of concrete life events and cross-platform behavior trajectories. Experiments show that ClawRec outperforms the strongest baselines, achieving an NDCG@20 of 0.6134 (+0.1126) and a Hit@20 of 0.6944 (+0.0854), while also improving user state quality and temporal alignment. Our code and dataset are available at https://github.com/RUCAIBox/ClawRec. △ Less

Submitted 26 July, 2026; originally announced July 2026.

Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning

Authors: Guanqun Zhao, Zijun Xie, Binbin Zheng, Enlei Gong, Jiafeng Lu, Yehan Yang, Aoqi Hu, Zeyu Chen

Abstract: Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse. Existing methods typically retain or discard tokens based solely on the magnitude of their importance ratios, applying the same threshold… ▽ More Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse. Existing methods typically retain or discard tokens based solely on the magnitude of their importance ratios, applying the same threshold uniformly across token positions. In this work, we reveal that the natural scale of the importance ratio varies systematically with token entropy. Under asynchronous dynamics, this entropy-ratio scaling dictates two distinct phenomena: at low entropy, the inherent train-inference discrepancy is drastically amplified into substantial sampling noise; at high entropy, in-flight weight updates naturally induce pronounced, legitimate exploratory deviations. Consequently, magnitude-only correction inadvertently admits the amplified noise while strictly masking out the essential exploration triggered by in-flight updates. To address this, we propose the Entropy-Scaled Trust Region (ESTR), which scales each token's off-policy deviation by its local entropy, requiring no auxiliary forward passes or explicit version-switch detection. Across long-horizon agentic tasks and mathematical reasoning benchmarks, ESTR consistently outperforms existing asynchronous methods and achieves the best train-inference consistency. It reaches $37.34$ avg@1 on BrowseComp-Plus and $95.69$ on multi-turn GSM8K, matching synchronous GRPO while achieving a $2.6\times$ speedup. △ Less

Submitted 3 August, 2026; v1 submitted 24 July, 2026; originally announced July 2026.

Can Generative Recommendation Reach Cold Items? A Temporal Perspective on Semantic-ID Generation

Authors: Jie Peng, Yanping Zheng, Zhewei Zhe, Bin Tong, Guan Wang, Bo Zheng

Abstract: Semantic-ID-based generative recommendation represents items as sequences of shared semantic tokens, enabling token recombination beyond isolated item IDs. However, closed-world recombination does not necessarily imply temporal open-token cold-start induction, where new items enter the item catalog with unseen atomic tokens or weakly supported SID paths. In this work, we revisit SID-based generati… ▽ More Semantic-ID-based generative recommendation represents items as sequences of shared semantic tokens, enabling token recombination beyond isolated item IDs. However, closed-world recombination does not necessarily imply temporal open-token cold-start induction, where new items enter the item catalog with unseen atomic tokens or weakly supported SID paths. In this work, we revisit SID-based generative recommendation under an absolute-time temporal protocol that separates seen and unseen targets and diagnoses the cold item reachability at the token level. Through seen/unseen-hit analysis, coldness taxonomy, and oracle-prefix probing, we show that current SID-based models can occasionally reach future items supported by observed tokens and prefixes, but struggle with unseen atomic tokens and unsupported SID paths. We further explain this boundary by interpreting SID generation as hierarchical semantic bucketing: early tokens select coarse semantic regions, while later tokens refine item-specific paths. These findings show that SID generation is compositional but not fully open-ended, and suggest future directions in more independent SID spaces, scoring-based interfaces, and dynamic textual context. △ Less

Submitted 23 July, 2026; originally announced July 2026.

CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning

Authors: Yubo Wang, Qiuyu Zhao, Zenghui Sun, Shichao Dong, Jinsong Lan, Xiaoyong Zhu, Haoyang Li, Bo Zheng, Lei Chen

Abstract: Memory Manager models are pivotal in agent systems. Existing methods rely predominantly on LLM-judged synthetic question-answer (QA) pairs, making memory valuation dependent on sampled queries and the downstream reader. To address this limitation, we propose \textbf{CMI-Mem}, a reinforcement learning(RL)-based lightweight memory manager model with a hybrid reward that combines downstream QA correc… ▽ More Memory Manager models are pivotal in agent systems. Existing methods rely predominantly on LLM-judged synthetic question-answer (QA) pairs, making memory valuation dependent on sampled queries and the downstream reader. To address this limitation, we propose \textbf{CMI-Mem}, a reinforcement learning(RL)-based lightweight memory manager model with a hybrid reward that combines downstream QA correctness and intrinsic Conditional Mutual Information (CMI). CMI evaluates the information contributed by new conversational inputs relative to the current memory state without conditioning on a sampled QA query, thereby complementing rather than replacing QA grounding. Our codes are available at: https://github.com/Wyb0627/CMIMem , and the CMI-Mem-4B model checkpoint is available at: https://www.modelscope.cn/models/wyb0627/CMIMem-4B △ Less

Submitted 15 July, 2026; originally announced July 2026.

Enhancing Relation Modeling with Social Attributes for Social Media Popularity Prediction

Authors: Bolun Zheng, Yuhao Luo, Wei Zhu, Ning Xu, An-An Liu, Lingyu Zhu, Canjin Wang

Abstract: Recent studies highlight the critical role of retrieval-augmented mechanisms in social media popularity prediction (SMPP). Although such frameworks have improved SMPP performance by leveraging historical posts, existing methods still suffer from the low retrieval accuracy due to the oversight of relative relationships among UGC instances. To address this limitation, we propose a novel Relation-Enh… ▽ More Recent studies highlight the critical role of retrieval-augmented mechanisms in social media popularity prediction (SMPP). Although such frameworks have improved SMPP performance by leveraging historical posts, existing methods still suffer from the low retrieval accuracy due to the oversight of relative relationships among UGC instances. To address this limitation, we propose a novel Relation-Enhanced Retrieval-Augmented framework (RE-Rag) that models UGC similarity as a continuous relation jointly driven by semantic content and social attributes. Specifically, RE-Rag employs a Semantic-Attribute Retriever (SAR) to obtain instances aligned in both semantic and social-attribute distributions. Subsequently, we design a Relation-Guided Predictor (RGP): first, cross-attention encodes multimodal features of retrieved instances; then, a relative relation graph is introduced to guide attention weight allocation, forming a Relation-Guided Transformer (RGTs) that dynamically modulate attention weights based on relative attribute relations to capture the interplay between semantics and various social attributes. The refined features are fused with the target instance for popularity prediction. Experiments on three public benchmarks show that RE-Rag consistently outperforms state-of-the-art methods in both prediction accuracy and retrieval efficiency. △ Less

Submitted 21 July, 2026; originally announced July 2026.

TSGR: Taobao Search Generative Retrieval

Authors: Tianyu Zhan, Gui Ling, Tong Xiong, Kunhai Lin, Yang Wang, Kaixuan Zhang, Zhihong Chen, Yuliang Yan, Dan Ou, Shengyu Zhang, Haihong Tang, Bo Zheng

Abstract: Generative retrieval (GR) has demonstrated strong promise for industrial e-commerce search by training a single autoregressive model to directly generate the Semantic IDs (SIDs) of target items. However, existing GR systems are primarily optimized for semantic matching and remain insensitive to item business value: SID construction is value-unaware, and candidates are ranked without access to item… ▽ More Generative retrieval (GR) has demonstrated strong promise for industrial e-commerce search by training a single autoregressive model to directly generate the Semantic IDs (SIDs) of target items. However, existing GR systems are primarily optimized for semantic matching and remain insensitive to item business value: SID construction is value-unaware, and candidates are ranked without access to item side-info. Consequently, high-value items are often missed or deprioritized at the retrieval stage, limiting downstream business impact. This limitation is particularly critical in industrial settings such as Taobao Search, where business objectives are central to system design. To address this, we propose $\textbf{T}$aobao $\textbf{S}$earch $\textbf{G}$enerative $\textbf{R}$etrieval ($\textbf{TSGR}$), a unified generative retrieval framework that incorporates value awareness into both item representation and candidate ranking. 1) For item representation, TSGR introduces $\textbf{Query-aware Parallel SID (QP-SID)}$, which encodes query-conditioned value orderings into the SID construction by building parallel codebooks derived from query-item statistics, so that higher-value and query-relevant items are assigned better token indices. 2) For candidate ranking, we introduce a $\textbf{Value-aware Ranking Module (VRM)}$ that is built upon and jointly optimized with the GR, enabling a single model to seamlessly serve as both retriever and pre-ranker without a dedicated pre-ranking stage. A progressive training pipeline further aligns the model with semantic relevance, user preferences, and business objectives. Offline experiments show that TSGR achieves a 9.16\% improvement in HR@1000, and online A/B tests further validate its effectiveness, yielding gains of +0.43\% in IPV, +1.12\% in Transaction Count, and +1.64\% in GMV. TSGR has been fully deployed in production. △ Less

Submitted 22 July, 2026; v1 submitted 21 July, 2026; originally announced July 2026.

Surprise Forcing: What to Remember, When to Skip in Long Video Generation

Authors: Shuwei Shi, Zhen Li, Muyao Niu, Chuanhao Li, Bo Zheng, Kaipeng Zhang, Yinqiang Zheng

Abstract: Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources uniformly across a highly non-stationary sequence. A rolling key-value cache forgets distant visual evidence even when that evidence remains important, while every generated chunk receives the same number of denoising passes irrespective of its ac… ▽ More Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources uniformly across a highly non-stationary sequence. A rolling key-value cache forgets distant visual evidence even when that evidence remains important, while every generated chunk receives the same number of denoising passes irrespective of its actual difficulty. We introduce Surprise Forcing, a training-free framework that treats both limitations as online resource-allocation problems. A Surprise-Gated Memory Bank summarizes evicted frames with value-token descriptors, evaluates them using complementary global-deviation and nearest-neighbor novelty signals, and regulates admission through a feedback-controlled budget in normalized score space. Priority-based replacement and relevance-aware routing then keep the external memory compact and useful. In parallel, Surprise-Aware Denoising estimates chunk difficulty from the maximum adjacent-frame cosine distance after the first denoising pass and uses a local percentile scheduler to skip intermediate steps for comparatively easy chunks. Experiments on VBench, VBench-Long, and VBench-2.0 show that the proposed allocation strategy improves long-horizon consistency and visual quality while retaining real-time streaming throughput. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Comments: Technical report

Pailitao-MMSearch: Building Native E-Commerce Multimodal Search Foundation

Authors: Xiaohan Ye, Xu Chen, Zihan Gong, Jian Ding, Lianyu Du, Baicheng Chen, Yunmeng Shu, Jingqian Zhao, Zhixiang Zhao, Shuaiqi Jia, Chong Ma, Shuwen Xiao, Xiangheng Kong, Yuan Gao, Jun Song, Jinsong Lan, Xiaoyong Zhu, Bo Zheng

Abstract: The evolution of e-commerce has fundamentally transformed how users search for products, shifting from simple text-based keyword queries to complex multimodal interactions that seamlessly combine product images, natural language descriptions, and mixed-intent instructions. However, existing approaches face a critical dilemma: single-modal specialist models, deployed independently for text retrieva… ▽ More The evolution of e-commerce has fundamentally transformed how users search for products, shifting from simple text-based keyword queries to complex multimodal interactions that seamlessly combine product images, natural language descriptions, and mixed-intent instructions. However, existing approaches face a critical dilemma: single-modal specialist models, deployed independently for text retrieval, visual search, and voice recognition, operate in isolation and cannot handle cross-modal queries, while general-purpose vision-language models lack the domain-specific knowledge necessary for fine-grained product understanding, user behavior modeling, and commercial intent reasoning. In this work, we present Pailitao-MMSearch, one native e-commerce multimodal search foundation model designed to bridge this gap. Our approach introduces three key innovations: (1)HybSID (Hybrid Semantic ID);(2)a two-stage continual pre-training strategy; and (3)a hybrid reasoning post-training pipeline. Built upon Qwen and deployed on Taobao's Pailitao multimodal search platform, Pailitao-MMSearch achieves substantial improvements in online A/B testing, including up to +13.61\% in Gross Merchandise Volume (GMV) and +8.21\% in transaction volume compared to traditional multi-modal search pipeline, demonstrating the effectiveness of our native e-commerce multimodal search large language models. △ Less

Submitted 19 July, 2026; originally announced July 2026.

Comments: Technical Report: Pailitao-MMSearch

Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation

Authors: Zesen Zhao, Minkyoung Cho, Hui shen, Boyuan Zheng, Kunxiao Gao, Yulong Cao, Z. Morley Mao

Abstract: Test-time scaling improves foundation-model inference by spending additional computation, but robot control requires deciding whether extra compute is useful before executing an action. World Action Models (WAMs) make this decision natural: each rollout exposes both an action chunk and predicted future observations. We propose \methodgated, a training-free selective test-time scaling framework for… ▽ More Test-time scaling improves foundation-model inference by spending additional computation, but robot control requires deciding whether extra compute is useful before executing an action. World Action Models (WAMs) make this decision natural: each rollout exposes both an action chunk and predicted future observations. We propose \methodgated, a training-free selective test-time scaling framework for WAMs. We first instantiate \method, a fixed-budget Best-of-$N$ selector that ranks sampled rollouts by cross-view depth reprojection consistency of their predicted futures, computed with a frozen geometry foundation model. \methodgated\ adds a lightweight action--future consistency gate that invokes \method\ only when the initial rollout appears internally inconsistent. Across five benchmark--backbone settings on RoboCasa, LIBERO Long, and RoboTwin~2.0, fixed-budget \method\ improves $N{=}8$ task success in every setting, e.g., raising the RoboCasa group average from $66.3\%$ to $68.4\%$ with Cosmos Policy and from $80.8\%$ to $82.5\%$ with X-WAM. With gating enabled, \methodgated\ recovers on average $74.8\%$ of the always-on success gain while triggering additional sampling on only $26.2\%$ of decision points. Offline diagnostics show that cross-view reprojection is a strong task-label-free selector, and we identify false low-score selections as a failure mode that helps explain why performance can saturate or degrade as $N$ increases. △ Less

Submitted 19 July, 2026; originally announced July 2026.

Comments: Extened version of CVPR 2026 EAI workshop

AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization

Authors: Yuejia Dou, Hesong Wang, Xinyu Zhang, Tianyu Wang, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, Qi Qi

Abstract: Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals. The emerging AI-Generated Bidding (AIGB) paradigm widely adopts generative modeling to optimize bidding strategies, yet suffers from the limited mode coverage of offline datasets and inadequate task-state understanding, hindering effective exploration of opti… ▽ More Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals. The emerging AI-Generated Bidding (AIGB) paradigm widely adopts generative modeling to optimize bidding strategies, yet suffers from the limited mode coverage of offline datasets and inadequate task-state understanding, hindering effective exploration of optimal strategies. Large Language Models (LLMs), with prior world knowledge and reasoning capabilities, offer a promising approach to overcome these limitations. However, directly applying LLMs to auto-bidding tasks faces inherent challenges in limited numerical precision, hallucinations, and inference latency. To address these limitations, we propose AIGB-R1, a hierarchical self-evolving auto-bidding framework aiming to enhance AI-Generated Bidding via LLMs' Reasoning capabilities, comprising a high-level Planner module for macro-level strategy planning and a low-level Executor module for fine-grained decision-making. Building upon this, we design an experience-driven self-evolving loop, enabling autonomous strategy exploration and optimization from accumulated experience. We adopt a two-stage pipeline of offline pre-training and post-training alignment, and build an interactive bidding simulation environment for strategy rollout. Furthermore, we propose Decoupled Group Relative Policy Optimization (D-GRPO) to achieve end-to-end optimization via advantage decoupling. Experimental results on a large-scale public dataset demonstrate the effectiveness of AIGB-R1. △ Less

Submitted 19 July, 2026; originally announced July 2026.

RecGPT-V3 Technical Report

Authors: Bowen Zheng, Chao Yi, Dian Chen, Gaoyang Guo, Han Zhu, Jiakai Tang, Jian Wu, Mao Zhang, Wen Chen, Yifan Lu, Yujie Luo, Yuning Jiang, Zhujin Gao, Bo Zheng, Chenchi Zhang, Dixuan Wang, Hao Fang, Jiancai Liu, Jing Yu, Junjun Zheng, Ke Chen, Kewei Zhu, Mengyan Li, Mingke Xu, Wenjun Yang , et al. (4 additional authors not shown)

Abstract: Large language models (LLMs) are transforming recommender systems from matching co-occurrence patterns in historical behavior toward reasoning about the intent that drives it. RecGPT-V1 pioneered this paradigm on Taobao by centering user understanding, and RecGPT-V2 scaled it via coordinated multi-agent reasoning; both are deployed in production with consistent gains in user experience and commerc… ▽ More Large language models (LLMs) are transforming recommender systems from matching co-occurrence patterns in historical behavior toward reasoning about the intent that drives it. RecGPT-V1 pioneered this paradigm on Taobao by centering user understanding, and RecGPT-V2 scaled it via coordinated multi-agent reasoning; both are deployed in production with consistent gains in user experience and commercial outcomes. However, operating RecGPT at scale reveals three challenges: (1) stateless behavior modeling, where each request reprocesses full user history, wasting computation and discarding prior analysis; (2) a tag-to-item information bottleneck, where natural-language tags form a lossy channel between user understanding and item grounding; and (3) inefficient explicit reasoning, whose lengthy chain-of-thought incurs untenable latency and compute overhead. We present RecGPT-V3, a stateful, hybrid-modal recommender that reasons over natural language for open-world knowledge and Semantic IDs (SIDs) for concrete item grounding. A Memory Hub maintains structured, continually evolving user memory that distills long-horizon behavior into condensed units, cutting user-modeling computation by 55.8%. A Hybrid-modal Foundation Model allows the LLM jointly reason over text tags and SIDs, opening a high-bandwidth channel into the item space. Latent Intent Reasoning internalizes verbose rationales into compact learnable latent tokens that remain decodable into readable explanations, lowering output token cost by 200x. Deployed in Taobao's "Guess What You Like" feed, RecGPT-V3 achieves consistent gains in large-scale online A/B tests: IPV +1.28%, CTR +1.00%, TC +1.97%, GMV +3.97%, while cutting end-to-end serving resource consumption by 52.4%. △ Less

Submitted 24 July, 2026; v1 submitted 16 July, 2026; originally announced July 2026.

Comments: Technique Report

PReM: Learning What to Preserve and When to Refresh for Context Compression

Authors: Bohan Yu, Lei Shen, Chenxi Zhou, Chen Han, Junlin Liu, Wenbo Su, Yu Cheng, Bo Zheng

Abstract: Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing compression-oriented approaches, such as key-value (KV) cache compression and context compression, often either make an early decision about which contextual information to keep or rely on an external compressor. Such design… ▽ More Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing compression-oriented approaches, such as key-value (KV) cache compression and context compression, often either make an early decision about which contextual information to keep or rely on an external compressor. Such designs make it difficult to adapt the compressed context to the evidence needed by later reasoning steps. This paper introduces PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it. Specifically, PReM uses a dedicated memory layer to make memory-selection decisions, and a special memory token <m> to trigger refreshes during generation. To train this behavior, PReM introduces Phase-Separated Refresh Training, aligning memory selection with memory-conditioned generation while preserving continuity across refreshes. Experiments with 32K-token contexts show that PReM outperforms strong baselines under both 16x and 32x compression, while maintaining a favorable balance between answer quality and inference efficiency. △ Less

Submitted 15 July, 2026; originally announced July 2026.

Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget

Authors: Guoxuan Chen, Chufeng Xiao, Haoran Yang, Siyue Xie, Binxiao Huang, Ming Zhang, Cheuk Him Chau, Xinyu Fu, Yingzhao Lian, Tom S. Y. Li, Jintao Lin, Bowen Dong, Zian Qian, Yuhao Liu, Yuxuan Hu, Weikang Shi, Bin Zou, Bowen Zheng, Haoxuan Che, Chang Chen, Yuyang He, Heyang Sun, Tianyu Huang, Chong Hou Choi, Cheng Gong , et al. (8 additional authors not shown)

Abstract: We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turbo variants. It delivers competitive performance in high-quality text-to-image generation, fast inference, instruction-based editing, and bilingual (Chinese-English) text rendering. Closed-source multimodal systems like Nano-Banana-Pro and GPT-Image-2… ▽ More We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turbo variants. It delivers competitive performance in high-quality text-to-image generation, fast inference, instruction-based editing, and bilingual (Chinese-English) text rendering. Closed-source multimodal systems like Nano-Banana-Pro and GPT-Image-2 achieve strong performance through system-level integration rather than a single model, yet their internal practices remain largely undisclosed. In this work, we demonstrate that strengthening the understanding capability of the system, through a stronger multimodal encoder, agentic prompt rewriting, and related techniques, together with improvements in data quality, training pipelines, and agentic inference-time scaling, can substantially enhance generation and editing performance even under highly constrained compute budgets. Comprehensive evaluations show that Boogu-Image-0.1 consistently matches or surpasses other open-source models across standard benchmarks, and achieves results approaching leading closed-source systems. Notably, this is accomplished with only 208.62 million unique images. The base model's theoretical training cost is only approximately \$400K. We share practical discussions that we believe are valuable to the broader research community, and release weights, code, and recipes under Apache 2.0 to advance the open ecosystem for unified multimodal understanding and generation. Our code is available here: https://github.com/Boogu-Project/Boogu-Image. △ Less

Submitted 18 July, 2026; v1 submitted 14 July, 2026; originally announced July 2026.

Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

Authors: Gong Sitong, Tianyu Yan, Caixin Kang, Bo Zheng, Xiang Ruan, Huchuan Lu, Kaipeng Zhang, Yoichi Sato, Yifei Huang

Abstract: When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving context that enables a new form of assistance: one that is proactive rather than merely reactive. Yet existing approaches either wait passively for user queries or treat every detected event as requiring a response, without considering the user's history, current activity, or whethe… ▽ More When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving context that enables a new form of assistance: one that is proactive rather than merely reactive. Yet existing approaches either wait passively for user queries or treat every detected event as requiring a response, without considering the user's history, current activity, or whether assistance would actually be welcome. We reframe proactive assistance as a context-dependent decision problem: the agent must not only perceive what is happening, but reason over accumulated temporal context to determine when and whether to intervene. To this end, we present Vinci2, a proactive egocentric assistance system that advances the on-device assistant Vinci from reactive response toward proactivity. On the evaluation side, we present EgoServe, the first large-scale benchmark for proactive assistance in continuous egocentric video. EgoServe comprises over 3,000 service instances organized along 4 temporal memory horizons, ranging from immediate safety alerts to long-term habit coaching, across 10 service categories. On the modeling side, we propose EgoMemo, a training-free, memory-augmented agent that maintains three complementary memory representations: multi-scale temporal summaries, a semantic knowledge graph, and visual embedding archives. At each timestep, EgoMemo performs retrieval-augmented reasoning to determine whether assistance is warranted and, if so, produces contextually grounded responses. Experiments demonstrate that EgoMemo establishes strong baselines on EgoServe while remaining competitive on existing egocentric benchmarks. Our benchmark and code are publicly available at \href{https://sitonggong.github.io/EgoServe-page/}{Vinci2}. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Comments: Accepted by ECCV 2026

Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval

Authors: Gui Ling, Zhihong Chen, Yu Li, Tong Xiong, Kunhai Lin, Kaixuan Zhang, Yuliang Yan, Dan Ou, Haihong Tang, Bo Zheng

Abstract: Generative Retrieval (GR) formulates retrieval as a sequence-to-sequence generation task, assigning each document a document identifier (DocID) and retrieving it through autoregressive decoding, making DocID design a critical factor in retrieval quality. However, existing schemes based on discrete representation learning suffer from inherent collision issues and create a mismatch between the DocID… ▽ More Generative Retrieval (GR) formulates retrieval as a sequence-to-sequence generation task, assigning each document a document identifier (DocID) and retrieving it through autoregressive decoding, making DocID design a critical factor in retrieval quality. However, existing schemes based on discrete representation learning suffer from inherent collision issues and create a mismatch between the DocID's encoding objective and the system's business optimization target. To address these limitations, we propose Cluster-Ranked Identifier (CRID), which decouples DocID into semantic clustering and business-value ranking, yielding collision-free identifiers that support incremental updates via intra-cluster reranking. We further introduce an analytical framework that decomposes retrieval gains into personalized preference and statistical prior generalization, revealing how semantic cluster size governs the balance between the two components. Experiments on a 300M-item Taobao e-commerce corpus show that CRID surpasses the strongest embedding-based retrieval baseline on top-K Hitrate, and delivers +1.06% GMV in full-traffic deployment. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Prompt Generation Technical Report

Authors: Dan Ou, Gui Ling, Hao Wan, Hongbin Zhou, Jialiang Cheng, Jiangnan Pang, Silu Zhou, Wei Shi, Weichen Ye, Wenming Zhang, Yang Wang, Yu Li, Yuliang Yan, Zhan Fa, Zhihong Chen, Zongyuan Wu, Bo Zheng, Changfa Wu, Dunxian Huang, Haihong Tang, Jinlong Guo, Kaixuan Zhang, Kun Ma, Lin Qu, Longbo Zhong , et al. (3 additional authors not shown)

Abstract: Generative retrieval has become an increasingly adopted paradigm for industrial search, recommendation, and advertising systems, delivering significant online gains. Most existing work combines user behavior sequences with large language models (LLMs) to model user preferences. In practice, feature engineering remains critical to model effectiveness, yet its complexity slows offline iteration and… ▽ More Generative retrieval has become an increasingly adopted paradigm for industrial search, recommendation, and advertising systems, delivering significant online gains. Most existing work combines user behavior sequences with large language models (LLMs) to model user preferences. In practice, feature engineering remains critical to model effectiveness, yet its complexity slows offline iteration and makes online deployment heavy and hard to reuse, all under tight online latency budgets. The root cause is a tight coupling between feature-processing logic and model architecture, where every feature change touches the training and serving code and resists reuse across scenarios. To break this coupling, we present Prompt Generation (PG), a high-level tokenizer and configuration-driven framework that decouples feature-processing logic from model architecture through two declarative JSON files, which serve as the single source of truth for both offline training and online serving, ensuring feature consistency across the two stages. Organizing features under four types with three composable processing components to assemble and compress heterogeneous features, PG delivers acceleration at three levels: (1)fast training iteration: feature experiments require only configuration changes, with built-in token compression for ultra-long sequences; (2)fast deployment: a new scenario only needs to conform to the PG schema and plug into a universal pipeline, with no scenario-specific engineering; (3)fast online inference: engine applies unified optimizations over the standardized configuration, reducing PG's overhead to a negligible level. PG has been deployed on Taobao Search with statistically significant online A/B uplifts of +0.47% in transaction count and +0.51% in GMV, and has been applied across multiple Taobao search and recommendation teams as the iteration framework for generative retrieval. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Continuous Query for Top-$K$ Maximal Sum Intervals over Streaming Data

Authors: Zhongshuai Zhang, Xiaochun Yang, Baihua Zheng, Rui Zhu, Haomin Li, Bin Wang

Abstract: The continuous identification of top-$k$ maximal sum intervals using a sliding window over a data stream is a critical operation for applications in IoT and beyond. A maximal sum interval is a non-overlapping, contiguous subsequence with the maximal sum in a sequence of signed values. Existing algorithms are ill-suited for streaming contexts: they either exhaustively enumerate all intervals even f… ▽ More The continuous identification of top-$k$ maximal sum intervals using a sliding window over a data stream is a critical operation for applications in IoT and beyond. A maximal sum interval is a non-overlapping, contiguous subsequence with the maximal sum in a sequence of signed values. Existing algorithms are ill-suited for streaming contexts: they either exhaustively enumerate all intervals even for small $k$ values, or depend on indexes that require frequent and costly restructuring. We propose a novel partition-based strategy. Our core insight is a partitioning scheme that guarantees that any maximal sum interval is fully contained within a single partition, enabling independent and parallel processing. This design provides two key advantages: it enables safe pruning of partitions that cannot contribute to top-$k$ results, drastically narrowing the search space, and it enables efficient, incremental maintenance of the maximal sum intervals in each partition. We develop algorithms for partition construction, incremental partition updates, and partition-based top-$k$ maximal sum interval search. Extensive experiments on real and synthetic datasets demonstrate that our approach significantly improves efficiency. △ Less

Submitted 12 July, 2026; originally announced July 2026.

Comments: 14 pages, 10 figures. Accepted by VLDB 2026 (PVLDB Vol. 19, No. 9)

Towards Autonomous and Auditable Medical Imaging Model Development

Authors: Shengyuan Liu, Jia-Xuan Jiang, Boyun Zheng, Cheng Wang, Zipei Wang, Wentao Pan, Hongtao Wu, Houwen Peng, Yu Gu, Lichao Sun, Yixuan Yuan

Abstract: Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific experimentation and strict requirements for validation protocols and prediction artifacts. Here we introduce AMID, an auton… ▽ More Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific experimentation and strict requirements for validation protocols and prediction artifacts. Here we introduce AMID, an autonomous multi-agent framework for medical imaging model development. AMID first proposes Data-Conditioned Method Planning, which refines coarse task-level search spaces into executable, parallelizable method lanes grounded in task-specific data analysis and runnable medical-imaging resources. It then develops Verification-Guided Two-Stage Optimization, moving from broad early exploration of diverse method lanes to selective exploitation of promising candidates while enforcing strict verification of validation protocols, metric computation, and prediction artifacts throughout the optimization. Across 20 medical imaging challenge tasks spanning diverse modalities and prediction types, AMID outperformed evaluated general-purpose MLE systems and, on several tasks, approached or matched strong human-designed challenge solutions. These results suggest that AMID can turn task-specific medical imaging model development from bespoke manual engineering into an agentic workflow for producing high-performing and auditable model artifacts across heterogeneous tasks. △ Less

Submitted 11 July, 2026; originally announced July 2026.

Comments: 18 Pages

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech

Authors: Ho Lam Chung, Bo-Xuan Zheng, Cheng-Chieh Huang, Cheng-Han Chang, Jung-Ching Chen, Lok-Lam Ieong, Ting-Lin Hsiao, Yu-Cheng Lee, Yi-Hsin Chung, Yu-Kai Guo, Hung-yi Lee

Abstract: Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment common Taiwanese text, and their pronunciation degrades at code-switching boundaries where Chinese and English alternate within one utterance. These problems share one root: the text side lacks adaptation to the Taiwanese context. We address the text s… ▽ More Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment common Taiwanese text, and their pronunciation degrades at code-switching boundaries where Chinese and English alternate within one utterance. These problems share one root: the text side lacks adaptation to the Taiwanese context. We address the text side from the bottom up. PangolinTokenizer, a byte-level BPE tokenizer trained on Taiwan-context data, reaches the lowest token rate (0.485 tokens/character) with the smallest vocabulary among nine tokenizers. Barbet, a billion-parameter Traditional-Chinese language model trained on PangolinTokenizer, serves as the text-semantic frontend and ranks first among comparable public models on a 14-task evaluation. BlueMagpie-TTS attaches Barbet to the pretrained acoustic stack of VoxCPM2 through a learned bridge, keeping the acoustic stack fixed. On a 1000-sentence Taiwan-localized test set, it lowers CER from 11.45% to 4.81% and WER from 14.83% to 5.36%, relative reductions of 58.0% and 63.9%. In a blind listening study on 500 of these sentences with ten listeners, 65.6% of majority votes prefer BlueMagpie-TTS. △ Less

Submitted 7 July, 2026; originally announced July 2026.

LEGATO 2: Toward Multimodal Sheet Music Recognition and Understanding

Authors: Guang Yang, Brian Siyuan Zheng, Victoria Ebert, Noah A. Smith

Abstract: We propose a novel pipeline, Legato 2, for extracting symbolic notation and semantic knowledge from images of sheet music. Legato 2 features the first large-scale neural model for optical music recognition (OMR) to operate sequentially on a system-by-system basis, following the horizontal lines of notation as they are read on the page, rather than treating the page as an undifferentiated image, en… ▽ More We propose a novel pipeline, Legato 2, for extracting symbolic notation and semantic knowledge from images of sheet music. Legato 2 features the first large-scale neural model for optical music recognition (OMR) to operate sequentially on a system-by-system basis, following the horizontal lines of notation as they are read on the page, rather than treating the page as an undifferentiated image, enabling better scaling to arbitrarily long inputs. It is also the first OMR model capable of generating symbolic transcriptions that include embedded textual content, such as titles and annotations. The pipeline combines system-level segmentation with an autoregressive vision-LM to capture both local notation details and score structure. Across multiple datasets, Legato 2 consistently outperforms prior state of the art. We also show that symbolic transcriptions complement visual inputs for frontier language models, improving their interpretation of dense musical documents. Legato 2 establishes new state-of-the-art performance in both OMR and downstream sheet music understanding. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: 23 pages. Equal contribution: Guang Yang and Brian Siyuan Zheng

ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate

Authors: Zijun Xie, Yuyang You, Yongzhi Li, Enlei Gong, Quan Chen, Yanhua Cheng, Peng Jiang, Binbin Zheng, Xiaolong Liu, Zeyu Chen, Yadong Mu

Abstract: Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their unequal contributions to the reasoning process. Entropy provides a natural indicator of the model's decision state, yet using it for token-level credit assignment presents two key challenges: long-tail probabilities in… ▽ More Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their unequal contributions to the reasoning process. Entropy provides a natural indicator of the model's decision state, yet using it for token-level credit assignment presents two key challenges: long-tail probabilities in large vocabularies corrupt both entropy values and gradients, and uncertainty carries distinct semantics across positive- and non-positive-advantage trajectories. We propose Asymmetric Credit Policy Optimization (ACPO), which replaces global entropy with the complement of the top-token probability as a mode-local proxy. Guided by gradient analysis, ACPO incorporates mismatch routing and saturation correction to shape policy updates into the desired asymmetric form, emphasizing uncertain decisions on positive trajectories while penalizing confident regions on failed ones. Theoretically, ACPO locally preserves the advantage direction while bounding surrogate error. Experiments on mathematical and coding reasoning benchmarks, including AIME 2025 and HumanEval Pro, show that ACPO consistently outperforms both entropy-aware methods (e.g., 80/20, GTPO) and strong outcome-supervised RL baselines (e.g., DAPO, SAPO). △ Less

Submitted 30 July, 2026; v1 submitted 3 July, 2026; originally announced July 2026.

Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction

Authors: Weiyi Xue, Fan Lu, Chi Zhang, Tianhang Wang, Sanqing Qu, Zehan Zheng, Boyuan Zheng, Junqiao Zhao, Guang Chen

Abstract: 3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this case, supervising Gaussians initialized from low-frequency sparse points with high-frequency images often induces uncontrolled densification and redundant primitives, d… ▽ More 3D Gaussian Splatting has demonstrated remarkable potential in novel view synthesis. In contrast to small-scale scenes, large-scale scenes inevitably contain sparsely observed regions with excessively sparse initial points. In this case, supervising Gaussians initialized from low-frequency sparse points with high-frequency images often induces uncontrolled densification and redundant primitives, degrading both efficiency and quality. Intuitively, this issue can be mitigated with scheduling strategies, which can be categorized into two paradigms: modulating target signal frequency via densification and modulating sampling frequency via image resolution. However, previous scheduling strategies are primarily hardcoded, failing to perceive the convergence behavior of scene frequency. To address this, we reframe the scene reconstruction problem from the perspective of signal structure recovery and propose SIG, a novel scheduler that synchronizes image supervision with Gaussian frequencies. Specifically, we derive the average sampling frequency and bandwidth of 3D representations, and then regulate the training image resolution and the Gaussian densification process based on scene frequency convergence. Furthermore, we introduce Sphere-Constrained Gaussians, which leverage the spatial prior of initialized point clouds to control Gaussian optimization. Our framework enables frequency-consistent, geometry-aware, and floater-free training, achieving state-of-the-art performance by a substantial margin in both efficiency and rendering quality in large-scale scenes. The code is available at: https://github.com/weiyixue999/Signal_Structure_Aware_Gaussian △ Less

Submitted 6 July, 2026; v1 submitted 2 July, 2026; originally announced July 2026.

AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization

Authors: Tianhong Zhou, Mingyang Han, Boyu Li, Yuxuan Jiang, Jiaxin Ye, Dongxiao Wang, Haoxiang Shi, Kunpeng Wang, Jun Song, Cheng Yu, Bo Zheng

Abstract: Audio-visual feature extraction is a fundamental component of multimodal understanding and generation tasks. However, existing evaluation protocols for feature extraction models exhibit dimensional bias, typically focusing on either semantic matching or temporal offset detection. Moreover, their data construction remains coupled, preventing independent assessment of temporal and semantic consisten… ▽ More Audio-visual feature extraction is a fundamental component of multimodal understanding and generation tasks. However, existing evaluation protocols for feature extraction models exhibit dimensional bias, typically focusing on either semantic matching or temporal offset detection. Moreover, their data construction remains coupled, preventing independent assessment of temporal and semantic consistency. We propose AV-SyncBench, the first benchmark to fully separate temporal and semantic evaluation for audio-visual synchronization. Built from in-the-wild videos, it spans Voice, Music, and Sound across 10 scenarios and 5 challenge tasks. Data are automatically filtered and manually verified to ensure on-screen sound sources. The benchmark contains 3,269 videos and 38,390 samples, and we evaluate five representative models to quantify feature quality for alignment and downstream tasks. The code and dataset are available at: https://fgt7t6g.github.io/AV-SyncBench. △ Less

Submitted 1 July, 2026; originally announced July 2026.

Comments: Accepted by Interspeech 2026

ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping

Authors: Jiacheng Chen, Tao Zhang, Manxi Lin, Dunxian Huang, Teng Shi, Honghao Fu, Mengyan Li, Xinming Zhang, Chenchi Zhang, Xuan Lu, Xiaoxiong Du, Haibin Chen, Shaolin Ye, Hao Chang, Xiaoqi Li, Shuwen Xiao, Yujin Yuan, Jingxuan Feng, Shaopan Xiong, Huimin Yi, Ju Huang, Qiu Shen, Ying Chen, Junjun Zheng, Xiangheng Kong , et al. (4 additional authors not shown)

Abstract: The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents. A common design wraps an LLM around existing search and recommendation pipelines, forcing complex intents through low-bandwidth retrieval or ranking interfaces and leaving a gap between language understanding and item-space fulfillment. Generative… ▽ More The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents. A common design wraps an LLM around existing search and recommendation pipelines, forcing complex intents through low-bandwidth retrieval or ranking interfaces and leaving a gap between language understanding and item-space fulfillment. Generative recommendation gives LLMs a direct item-space interface through semantic IDs (SIDs), but existing models mainly generate candidates for retrieval rather than translate flexible intents into item-space outcomes. We propose ShopX to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations into a single foundation model. We deploy ShopX in agentic shopping workflows through a model-native item-fulfillment framework with a serving harness that defines a model-facing action protocol and exposes support surfaces for context access, catalog grounding, and state management. Within this framework, ShopX plans and composes SID-based item-space operations such as SID beam-search retrieval, listwise ranking, or product bundling. This model-centric design reduces lossy hand-offs between agent orchestration and item-space execution. To build ShopX, we design semantically recoverable, LLM-operable SIDs and a training recipe that equips a general LLM for flexible multi-turn item-space fulfillment while retaining the knowledge and instruction-following abilities needed by a shopping agent. We evaluate the ShopX framework against tool-mediated agentic systems on single- and multi-turn fulfillment tasks derived from anonymized Taobao production logs, showing that model-native fulfillment improves overall framework behavior, especially on complex or ambiguous requests. △ Less

Submitted 15 July, 2026; v1 submitted 30 June, 2026; originally announced June 2026.

Comments: The new version adds additional results and details

ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

Authors: Zijun Xie, Binbin Zheng, Enlei Gong, Jihua Liu, Yuyang You, Lingfeng Liu, Jiayao Tang, Guanqun Zhao, Aoqi Hu, Zeyu Chen

Abstract: Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Context-management methods make such rollouts feasible by simplifying past interactions through deletion, folding, or memory editing. However, when useful history is collapsed into compressed states, the reconstructed context may no longer reveal which earlier ob… ▽ More Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Context-management methods make such rollouts feasible by simplifying past interactions through deletion, folding, or memory editing. However, when useful history is collapsed into compressed states, the reconstructed context may no longer reveal which earlier observations support a successful final answer. This creates a mismatch between bounded-context acting and outcome-based reinforcement learning: the policy acts on reconstructed context, while the learner lacks source-level provenance for assigning credit to the evidence that mattered. We propose ECHO, a selective turn-memory framework for traceable context reconstruction in Agentic RL. ECHO compresses each completed environment turn into a compact source-indexed memory record, reconstructs bounded policy contexts by selecting useful records, and reuses the selected source indices to route positive outcome credit to the final trajectory segment, reused evidence turns, memory findings, and memory-selection actions. On BrowseComp-Plus, ECHO reaches 43.4% held-out accuracy, outperforming GRPO at 28.9% and the rolling-summary baseline SUPO at 36.1%, while using fewer turns and lower trajectory volume than SUPO. The trained policy also improves zero-shot generalization across multi-objective QA, code generation, and deep information-seeking benchmarks on both dense and MoE backbones. △ Less

Submitted 3 August, 2026; v1 submitted 30 June, 2026; originally announced June 2026.

Antenna Orientation Optimization for Rotatable Antenna-Enabled ISAC Systems

Authors: Qingjie Wu, Beixiong Zheng, Guangchi Zhang, Robert Schober

Abstract: Non-fixed flexible antenna architectures, such as fluid antenna system (FAS), movable antenna (MA), and pinching antenna, have garnered significant interest in recent years. In this paper, we deploy a rotatable antenna (RA) array at the base station (BS) to improve the integrated sensing and communication (ISAC) performance by exploiting the additional spatial degrees of freedom (DoFs) introduced… ▽ More Non-fixed flexible antenna architectures, such as fluid antenna system (FAS), movable antenna (MA), and pinching antenna, have garnered significant interest in recent years. In this paper, we deploy a rotatable antenna (RA) array at the base station (BS) to improve the integrated sensing and communication (ISAC) performance by exploiting the additional spatial degrees of freedom (DoFs) introduced by antenna rotation. To enhance the sensing performance over an extended region containing a potential target while meeting the communication requirements of multiple users, we aim to maximize the minimum echo signal power within the sensing region, subject to required minimum communication rates of the users. For the special case of a single user and a point target, we show that the optimal orientation of all RAs is identical when both the communication user and the sensing target are located in the far-field region, and then derive a closed-form solution for the optimal RA pointing vector. For the general multi-user and extended-target case, we propose an alternating optimization (AO) algorithm that alternately optimizes the transmit beamforming for communication, the covariance matrix of the probing signal, and the pointing vectors of the RAs in an iterative manner. Simulation results demonstrate that the proposed RA-enabled ISAC system can significantly outperform various benchmark schemes, including systems with array-wise rotation optimization and fixed antenna orientation. △ Less

Submitted 2 July, 2026; v1 submitted 30 June, 2026; originally announced June 2026.

Comments: 13 pages, submitted to IEEE for possible publication

Contrastive Reflection for Iterative Prompt Optimization

Authors: Derek Koh, Jinghui Mo, Benjamin H. Le, Jiening Zhan, Baofen Zheng, Kevin Bevis, Nathaniel C. Owen, Lauren Elizabeth Charney, Wenqiong Liu, Jingwei Wu

Abstract: LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation. Improving the prompts that control these agents is an optimization problem, but in applied IR settings it often looks less like blind search and more like debugging. Engineers need to know which behavior failed, which nearby behavior still… ▽ More LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation. Improving the prompts that control these agents is an optimization problem, but in applied IR settings it often looks less like blind search and more like debugging. Engineers need to know which behavior failed, which nearby behavior still worked, what distinguishes the two, and whether a prompt edit improves held-out quality without introducing regressions. We present Contrastive Reflection, an iterative prompt-optimization framework for agentic IR workflows. The framework starts from a task-centric quality definition: QA agents expose retrieval or reasoning traces, and grading agents expose dimension-level scores and rationales. These structured traces are used to identify error-anchored behavioral slices, add nearby successful examples from the same region, and ask a Teacher LLM to propose a targeted prompt edit. Candidate edits are accepted only when validation performance improves, optionally subject to regression checks. We instantiate the framework with a tree-based slice selector, but the contribution is the contrastive reflection loop rather than the tree itself. On a public HotpotQA retrieval-augmented QA setup, one tree-selected contrastive repair improves held-out exact-match accuracy from 51.4% to 60.4%. Failure-only and random-evidence variants improve less and break more previously correct examples. A light instruction-only comparison places the method near modern prompt optimizers: MIPROv2 reaches 59.4% and GEPA 57.0%. The result is an interpretable optimization loop for IR agents, aimed at making prompt repair more inspectable and validation-driven. △ Less

Submitted 29 June, 2026; originally announced June 2026.

Comments: 6 pages, 1 figure. To appear at Agent4IR @ KDD 2026 (KDD 2026 Workshop on AI Agents for Information Retrieval)

ACM Class: I.2.7; H.3.3; I.2.6

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Authors: Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong, Weiming Wu, Jiayang Sun, Jiamin Song, Kaiqian Cui, Bowen Wang, Haoyuan Wu, Yitong Li, Dunjie Lu, Haikong Lu, Qi Zhen, Xinyuan Wang, Jiaqi Deng, Yuhao Yang, Cheng Chen, Boyuan Zheng, Alex Su, Xiao Yu, Hao Zou, Saaket Agashe, Xing Han Lu, Manpreet Kaur, Zhengyang Qi , et al. (11 additional authors not shown)

Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, designed to capture complex and challenging real-world phenomena. Each task represe… ▽ More Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, designed to capture complex and challenging real-world phenomena. Each task represents a realistic end-to-end workflow that takes human users a median of about 1.6 hours to complete and requires an average of 318 tool calls with Claude Opus 4.7 using maximum thinking, compared with about 30 in OSWorld 1.0. OSWorld 2.0 targets challenge phenomena that are common in real workflows yet underrepresented in prior benchmarks, spanning interaction-design challenges such as streaming interaction and dynamic environments, as well as agent-pattern challenges such as cross-source reasoning, implicit-state inference, and visual-spatial precision. Tasks are grounded in authentic input artifacts and cross-referenced against realistic stateful user profile data, and include separate safety reports auditing safety-sensitive execution. Under our primary binary-completion metric at 500 steps, Claude Opus 4.8 with maximum thinking and batched tool calls scores best but still completes only 20.6% of tasks at a 54.8% partial score; GPT-5.5 is far more token-efficient yet plateaus near 13%. These results show that current agents are still far from professional-level computer use: rather than stumbling on basic GUI control or coding, they lose track of constraints, miss information that arrives mid-task, guess rather than ask the user, and skip verification, struggling most when a task hinges on hidden state they must recover. △ Less

Submitted 13 July, 2026; v1 submitted 28 June, 2026; originally announced June 2026.

Comments: 68 pages, 42 figures. Equal contribution: Mengqi Yuan, Zilong Zhou, and Xinzhuang Xiong

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Authors: Jing Liang, Hongyao Tang, Yi Ma, Yancheng He, Weixun Wang, Xiaoyang Li, Ju Huang, Wenbo Su, Jinyi Liu, Yan Zheng, Jianye Hao, Bo Zheng

Abstract: Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. One vital cause is training-inference mismatch: LLM adopts separate inference and training engines for generation efficiency and training precision, which in practice exhibits inconsistent probabilities for the same traje… ▽ More Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. One vital cause is training-inference mismatch: LLM adopts separate inference and training engines for generation efficiency and training precision, which in practice exhibits inconsistent probabilities for the same trajectories on training and inference sides, even with synchronized model parameters. This naturally induces a special type of off-policyness ever existing and poisoning the training. Prior works have made various efforts in addressing the off-policyness to stabilize the training policies under the mismatch. In this paper, we point out the objective misalignment neglected by existing works that an effective update to the policy in the training engine not necessarily ensures the improvement of the inference policy, i.e., the one used in deployment. To this end, we propose a new policy optimization objective for LLM RL, named Monotonic Inference Policy Improvement (MIPI). Following this principle, we introduce Monotonic Inference Policy Update (MIPU), a two-step LLM RL framework that constructs sampler-referenced candidate updates and selectively accepts synchronized candidates using an inference-side gap proxy. Experiments conducted on two model scales under high mismatch show that MIPU improves average reasoning performance and training stability. △ Less

Submitted 28 June, 2026; originally announced June 2026.

Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search

Authors: Ping Liu, Qianqi Shen, Jianqiang Shen, Wenqiong Liu, Rajat Arora, Yunxiang Ren, Chunnan Yao, Dan Xu, Baofen Zheng, Wanjun Jiang, Andrii Soviak, Kevin Kao, Jingwei Wu, Wenjing Zhang

Abstract: Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles. We present an end-to-end RLAIF (Reinforcement Learning from AI Feedback) framework to generate \emph{portable} job search queries, terms that abstract away seeker-specific identifiers while preserving generalizable qualifications. This task introduces a high… ▽ More Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles. We present an end-to-end RLAIF (Reinforcement Learning from AI Feedback) framework to generate \emph{portable} job search queries, terms that abstract away seeker-specific identifiers while preserving generalizable qualifications. This task introduces a highly adversarial reward surface where policy optimization frequently exploits flaws in LLM-as-judge rubrics, resulting in degenerate verbatim-copying behaviors. We conducted comprehensive empirical experiments to isolate the impact of optimization mechanics against structured reward engineering. Our results demonstrate that for critic-free optimizers, performance is overwhelmingly dictated by robust reward shaping, rendering the specific choice of algorithm largely immaterial. While critic-free per-rollout baseline methods (RLOO and REINFORCE++) natively resist reward-hacking, the group-relative advantage normalization in GRPO appears uniquely sensitive to spurious reward signals, making it disproportionately susceptible to exploitation. We show that introducing a deterministic, rule-based reward floor to correct for rewards assigned to verbatim copying mitigates this failure mode, resulting in a substantial $+0.147$ quality improvement on a cross-family evaluation judge. Ultimately, we show that the training-time reward model inflates performance gains by $2.4\times$, confirming that the training success is fundamentally dependent on enforcing reward-shaping disciplines rather than selecting alternative optimizers. △ Less

Submitted 25 June, 2026; originally announced June 2026.

Comments: Accepted to KDD 2026 Workshop on AI Agent for Information Retrieval (Agent4IR)

Cross-Head Attention Uplift Network with Inverse Propensity Score under Unobserved Confounding

Authors: Haoran Zhang, Chuanpu Li, Yuxin Fu, Bin Tong, Guan Wang, Bo Zheng, Feng Zhou

Abstract: Uplift modeling, crucial for estimating individual treatment effects (ITE), faces dual challenges: flexibly leveraging inter-group similarity to enhance discriminative power and debiasing under unobserved confounding scenarios. In this paper, we propose the Cross-Head Attention Uplift Network (CHAUN) and Robust Adversarial Inverse Propensity Score (RA-IPS) method to address these limitations. CHAU… ▽ More Uplift modeling, crucial for estimating individual treatment effects (ITE), faces dual challenges: flexibly leveraging inter-group similarity to enhance discriminative power and debiasing under unobserved confounding scenarios. In this paper, we propose the Cross-Head Attention Uplift Network (CHAUN) and Robust Adversarial Inverse Propensity Score (RA-IPS) method to address these limitations. CHAUN employs shared feature embeddings and cross-head attention mechanisms to dynamically integrate treatment-specific and control-specific representations, enhancing inter-group correlation modeling. Theoretically, we prove that access to the true propensity scores ensures ITE identifiability even with unobserved confounders. For practical scenarios lacking true propensity scores, RA-IPS adversarially optimizes propensity weights within constrained uncertainty sets to mitigate bias from unobserved variables. Experiments on public datasets (CRITEO-UPLIFT, LAZADA) and a production e-commerce dataset demonstrate CHAUN's superiority over state-of-the-art uplift models, achieving relative improvements of up to 25.6% in QINI scores. RA-IPS further enhances robustness, outperforming standard IPS by 5.4% under unobserved confounding. The results validate the effectiveness of our proposed methods in real-world causal inference tasks. △ Less

Submitted 25 June, 2026; originally announced June 2026.

Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention

Authors: Xiao Li, Chengruidong Zhang, Hao Luo, Xi Lin, Zekun Wang, Zihan Qiu, Yunfei Mao, Langshi Chen, Man Yuan, Minmin Sun, Huiqiang Jiang, Siqi Zhang, Rui Men, Wei Hu, Gong Cheng, Bo Zheng, Dayiheng Liu, Jingren Zhou

Abstract: Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active correction is still anchored to that same write address. As a result, stale information stored at a different address cannot be actively removed before new content is written elsewhere. We propose Erase-then-Delta Attention… ▽ More Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active correction is still anchored to that same write address. As a result, stale information stored at a different address cannot be actively removed before new content is written elsewhere. We propose Erase-then-Delta Attention (EDA), a memory update rule that decouples where to erase from where to write. The key insight is that recurrent memory models should not only correct the current write, but also selectively suppress outdated memory at an independently chosen address. Concretely, our method first applies a targeted erase step along a learned erase direction, and then performs the standard delta-style corrective write along the current write direction. This preserves the corrective behavior of delta-rule updates while expanding their memory-management capacity. Language-model pretraining experiments across dense 2.5B and MoE 25B-A2.8B model families show that EDA performs best in both settings. The gain persists after 80B-token long-context midtraining of the MoE models, where EDA also performs best in long-context evaluations from 4k to 128k contexts. A compact update analysis and memory-state probes suggest why: EDA keeps the delta-rule corrective write intact while allocating an additional cleanup path most strongly when passive decay is weak. These results suggest that recurrent memory models should decide not only what to write, but also what stale information to erase and where. △ Less

Submitted 24 June, 2026; originally announced June 2026.

TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy

Authors: Hao Sun, Hao Yan, Mengting Chen, Quanjian Song, Yu Li, Juan Cao, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Sheng Tang

Abstract: While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms remains fundamentally constrained by a passive dependency on source camera trajectories, failing to accommodate the requisite interactive freedom for omnidirectional viewpoint exploration. To address this limitation, we define a pioneering research fr… ▽ More While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms remains fundamentally constrained by a passive dependency on source camera trajectories, failing to accommodate the requisite interactive freedom for omnidirectional viewpoint exploration. To address this limitation, we define a pioneering research frontier: Camera-controllable Video Virtual Try-on (CaM-VVT). Unlike conventional VVT, CaM-VVT not only necessitates viewpoint-agnostic texture hallucination but also strict structural synchronization between non-rigid human dynamics and background contexts under arbitrary, unconstrained camera movements. To tackle these challenges, we present TryOnCrafter, the first unified DiT-based framework specifically architected for the CaM-VVT task. Departing from implicit pixel-space manipulation, we introduce a Renderable 4D Try-on Proxy that explicitly decouples the human subject from the environment. This is achieved by distilling high-fidelity 2D try-on priors into a clothed 3DGS-based avatar, which is subsequently animated via SMPL-X sequences and metric-aligned into a reconstructed background point cloud. This proxy establishes a robust structural foundation with superior texture density and motion integrity. Our Proxy-Anchored Video DiT leverages this robust structural foundation as a primary geometric anchor, ensuring that the synthesized photorealistic videos are strictly constrained by prescribed trajectories and physically plausible deformations. Benefiting from the inherent editability of the 4D proxy, TryOnCrafter facilitates diverse downstream applications, including human relocalization, ``bullet time'' effects, and $360$-degree orbital viewing. △ Less

Submitted 3 July, 2026; v1 submitted 24 June, 2026; originally announced June 2026.

Comments: Project Page: https://sunhao242.github.io/TryOnCrafter_web.github.io/

OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation

Authors: Yingdong Hu, Haodong Zhu, Boyuan Zheng, Yihang Hu, Tong Zhang, Zunhao Chen, Junming Zhao, Ruiqian Nai, Yang Gao

Abstract: Whole-body humanoid loco-manipulation requires coordinating the robot's entire kinematic chain. However, most existing systems typically decouple the upper and lower bodies into separate controllers, limiting such coordination and yielding behaviors similar to those of a wheeled dual-arm platform. In this paper, we ask what it takes to build a whole-body native vision-language-action (VLA) model t… ▽ More Whole-body humanoid loco-manipulation requires coordinating the robot's entire kinematic chain. However, most existing systems typically decouple the upper and lower bodies into separate controllers, limiting such coordination and yielding behaviors similar to those of a wheeled dual-arm platform. In this paper, we ask what it takes to build a whole-body native vision-language-action (VLA) model that maps language and pixels directly to all of the humanoid's degrees of freedom. We conduct a systematic empirical study organized as a roadmap of one-variable-at-a-time experiments across three phases: whole-body teleoperation, VLA model design, and heterogeneous co-training. Our study yields several intriguing findings: a joint-based whole-body teleoperation interface outperforms alternatives that only partially expose the humanoid's degrees of freedom; a VLA pretrained on static and wheeled dual-arm platforms transfers surprisingly well to a humanoid's full action space; and co-training with HuMI, the humanoid analog of UMI, extends the policy to new objects and instructions without additional whole-body teleoperation on those targets. Following this roadmap yields OpenHLM, an open-source recipe for whole-body humanoid loco-manipulation. In a challenging long-horizon task that spans a wide vertical range of the humanoid, OpenHLM outperforms two state-of-the-art humanoid VLA baselines (GR00T N1.6 and $Ψ_0$) using less than half the total demonstration time. Our code, training data, and model checkpoints are available at [https://openhlm-project.github.io/]. △ Less

Submitted 20 June, 2026; originally announced June 2026.

Agentic Time Machine as an Infrastructure for Future-Event Forecasting

Authors: Jingyi Chai, Bingyang Zheng, Xiangrui Liu, Hao Lu, Zihang Zhou, Tianchen Wang, Kemeng Zhang, Siheng Chen

Abstract: Forecasting future events is a critical challenge for large language model (LLM) agents, spanning domains from elections and monetary policy to financial markets. However, evaluating progress on this task presents a fundamental trade-off between efficiency and environment fidelity. While live evaluation benchmarks suffer from an inherently slow feedback loop, existing retrospective replays typical… ▽ More Forecasting future events is a critical challenge for large language model (LLM) agents, spanning domains from elections and monetary policy to financial markets. However, evaluating progress on this task presents a fundamental trade-off between efficiency and environment fidelity. While live evaluation benchmarks suffer from an inherently slow feedback loop, existing retrospective replays typically restrict agents to static, pre-frozen databases that sacrifice the environmental realism of actual deployments. To tackle this issue, we introduce Agentic Time Machine (TM), an infrastructure that approximately reconstructs the web state at any chosen past time by filtering post-cutoff content. Leveraging this evaluation infrastructure, we further propose a planner-solver-aggregator multi-agent framework that breaks each question into diverse analytical angles, gathers evidence in parallel, and combines the results into a single forecast. Experiments show that offline scores under TM correlate strongly with live FutureX scores, validating that TM offers a fast and reliable sandbox for forecasting-agent evaluation. On FutureX-Past and Polymarket evaluated under TM, our framework achieves the highest score among strong closed-book, tool-augmented, and self-consistency baselines. On the official FutureX live leaderboard, our system achieves the best average rank over four consecutive weeks, including 1st place in May Week 1. As of June 17, it also ranks 1st on FutureX's official eight-week overall leaderboard. △ Less

Submitted 18 June, 2026; originally announced June 2026.

FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing

Authors: Yuxuan Jiang, Mingyang Han, Yusheng Dai, Andong Wang, Tianhong Zhou, Jiaxin Ye, Dongxiao Wang, Haoxiang Shi, Boyu Li, Jun Song, Cheng Yu, Bo Zheng, Weibei Dou, Zehua Chen, Jun Zhu

Abstract: Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge. However, existing methods struggle to balance temporal consistency with background preservation. In this paper, we propose FreeSonic, a training-free framework leveraging the state-of-the-art Rectified Flow-based TangoFlux model. FreeSonic utilizes an optimized… ▽ More Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge. However, existing methods struggle to balance temporal consistency with background preservation. In this paper, we propose FreeSonic, a training-free framework leveraging the state-of-the-art Rectified Flow-based TangoFlux model. FreeSonic utilizes an optimized inversion-reverse process and joint text-audio attention maps for precise target segment extraction. For content editing, a novel scheduled attention decoupling confines modifications to target regions while preserving original acoustic context. Furthermore, task-oriented noise injection enhances versatility for tasks such as audio removal and non-rigid replacement. Extensive experimental results demonstrate that FreeSonic achieves a superior balance by providing a high-fidelity and efficient solution for precise and consistent audio editing. Project and demos: https://free-sonic.github.io/ △ Less

Submitted 13 June, 2026; originally announced June 2026.

Comments: Accepted at Interspeech 2026