WZ
Weinan Zhang
cs.AIcs.LGcs.IRcs.CLcs.MAcs.ROstat.MLcs.CVcs.GTcs.SE
On Valency
published · living versionsW_uzyaurf4·v1 · currentpublished
MultiEvoSkill: Structure-Aware Multi-Agent Skill Evolution for Generalizable Skill Artifacts
with Kounianhua Du, Jianxing Liu, Ruoshui Shan, Yucheng Zhang +2
1 version
W_svgzshv6·v1published
W_d8gxv2zd·v1published
Preprints & journals
422 papers in the corpus · 2011–2026AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking2610.02831v1 · Wenteng Chen, Jiachen Zhu, Rong Shan et al.2026 · 0 citationsarXiv
NEXUS: Perceptive Whole-Body Control for Terrain-Adaptive Teleoperation2609.39000v1 · Xiangyu Miao, Junsong Wu, Jiyuan Shi et al.2026 · 0 citationsarXiv
SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations2609.39873v1 · Jun Guo, Xiaoshen Han, Qiwei Li et al.2026 · 0 citationsarXiv
InternW0-: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data2609.31394v1 · Xingyu Miao, Zizun Li, Baole Fang et al.2026 · 0 citationsarXiv
InternW0: A Foundational Physical World Model for Efficient Real-World Interactions2609.27656v1 · Jisong Cai, Yao Mu, Ganlin Yang et al.2026 · 0 citationsarXiv
Dissecting Advantage-Guided Post-Training for Vision-Language-Action Policies2609.28161v1 · Jiahang Cao, Hanye Zhao, Hang Lai et al.2026 · 0 citationsarXiv
MCPGen: Benchmarking LLMs on Executable MCPWorkflow Development2609.23925v1 · Yingxuan Yang, Jiaqi Liu, Lirui Guan et al.2026 · 0 citationsarXiv
Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents2609.16053v1 · Yuanyi Song, Yukai Wang, Xinbei Ma et al.2026 · 0 citationsarXiv
WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies2609.05591v1 · Lejun Zhang, Sarah Lu-Liang, Xin Jiang et al.2026 · 0 citationsarXiv
From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation2608.30461v1 · Junjie Huang, Jiarui Qin, Di Yin et al.2026 · 0 citationsarXiv
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents2608.27260v1 · Xingshan Zeng, Zishan Xu, Boju Zhang et al.2026 · 0 citationsarXiv
Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching2608.28695v1 · Rong Shan, Tianyi Xu, Congmin Zheng et al.2026 · 0 citationsarXiv
SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scale2608.22725v1 · Jiaqi Liu, Maolin Ran, Xiaoyang Lu et al.2026 · 0 citationsarXiv
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents2608.18852v1 · Qingyao Li, Wenxiang Jiao, Shuai Shao et al.2026 · 0 citationsarXiv
SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule Evolution2608.17468v1 · Maolin Ran, Xiaoyang Lu, Jiaqi Liu et al.2026 · 0 citationsarXiv
Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval2608.16071v1 · Lihui Ding, Zihan Guo, Bingwei Lu et al.2026 · 0 citationsarXiv
RoboStriker: Latent-Space Strategic Games for Autonomous Humanoid Boxing2608.16195v1 · Kangning Yin, Kaige Liu, Zhe Cao et al.2026 · 0 citationsarXiv
Learning from Unreachable Rewards: Hint-Conditioned Reinforcement Learning for Generative Recommendation2608.11980v2 · Kangning Zhang, Haotian Fang, Xukun Luo et al.2026 · 0 citationsarXiv
MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning2608.09130v1 · Hanye Zhao, Muning Wen, Yong Yu et al.2026 · 0 citationsarXiv
GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models2608.05948v1 · Shuai Wang, Yaxin Feng, Xuekun Jiang et al.2026 · 0 citationsarXiv
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning2608.06197v2 · Zishan Xu, Zhiyuan Yao, Yuxin Chen et al.2026 · 0 citationsarXiv
Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories2608.02276v1 · Shuai Shao, Kangning Zhang, Qingyao Li et al.2026 · 0 citationsarXiv
VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation2607.28590v1 · Kangning Zhang, Yixing Li, Shuai Shao et al.2026 · 0 citationsarXiv
Scaling Behavior Foundation Model for Humanoid Robots2607.15163v1 · Weishuai Zeng, Kangning Yin, Xiaojie Niu et al.2026 · 0 citationsarXiv
HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation2607.09776v2 · Shaopeng Zhai, Qi Zhang, Tianyi Zhang et al.2026 · 0 citationsarXiv
A Definition and Roadmap for World Models2607.06401v1 · Xinyuan Chen, Haoyu Guo, Shi Guo et al.2026 · 0 citationsarXiv
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization2607.04988v1 · Haoxiang Ma, Junhao Cai, Xiaoxu Xu et al.2026 · 0 citationsarXiv
Social Networks of LLM Agents2607.03695v1 · Kaixuan Liu, Guojun Xiong, Weinan Zhang et al.2026 · 0 citationsarXiv
Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration2606.30246v1 · Zihan Guo, Zeyi Chen, Zhiyu Chen et al.2026 · 0 citationsarXiv
EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies2606.18239v3 · Ning Gao, Jinliang Zheng, Xing Gao et al.2026 · 0 citationsarXiv
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation2606.15893v2 · Ning Li, Zixuan Guo, Yan Xu et al.2026 · 0 citationsarXiv
Retrospective Progress-Aware Self-Refinement for LLM Agent Training2606.14302v2 · Xinbei Ma, Congmin Zheng, Jiyang Qiu et al.2026 · 0 citationsarXiv
Communication Policy Evolution for Proactive LLM Agents2606.14314v1 · Xinbei Ma, Jiyang Qiu, Yao Yao et al.2026 · 0 citationsarXiv
SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior2606.11543v1 · Zhiyu Chen, Zihan Guo, Bo Huang et al.2026 · 0 citationsarXiv
DiffCold: A Diffusion-based Generative Model for Cold-Start Item Recommendation2606.12245v1 · Kangning Zhang, Yingjie Qin, Weinan Zhang et al.2026 · 0 citationsarXiv
AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing2606.09811v1 · Jisong Cai, Long Ling, Shiwei Chu et al.2026 · 0 citationsarXiv
Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents2606.05558v2 · Kaixuan Liu, Guojun Xiong, Weinan Zhang et al.2026 · 0 citationsarXiv
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents2606.06087v3 · Aofan Yu, Chenyu Zhou, Tianyi Xu et al.2026 · 0 citationsarXiv
SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval2606.00822v1 · Zicai Cui, Zihan Guo, Weiwen Liu et al.2026 · 0 citationsarXiv
DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval2605.31377v1 · Siyuan Qi, Xinyuan Wang, Yingxuan Yang et al.2026 · 0 citationsarXiv
Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents2605.25971v2 · Haoyi Hu, Qirong Lyu, Xianghan Kong et al.2026 · 0 citationsarXiv
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents2605.16986v2 · Jingxing Wang, Chenyu Zhou, Zhihui Fu et al.2026 · 0 citationsarXiv
SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory2605.15710v1 · Huacan Chai, Yukai Wang, Yingxuan Yang et al.2026 · 0 citationsarXiv
Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering2605.15721v1 · Jiachen Zhu, Zhuoying Ou, Congmin Zheng et al.2026 · 0 citationsarXiv
XSearch: Explainable Code Search via Concept-to-Code Alignment2605.16046v2 · Yiming Liu, Ruofan Liu, Yun Lin et al.2026 · 1 citationarXiv
Position: Agentic AI System Is a Foreseeable Pathway to AGI2605.12966v1 · Junwei Liao, Shuai Li, Muning Wen et al.2026 · 0 citationsarXiv
SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle2605.13139v1 · Hao Guan, Lingyue Fu, Shao Zhang et al.2026 · 0 citationsarXiv
MMSkills: Towards Multimodal Skills for General Visual Agents2605.13527v3 · Kangning Zhang, Shuai Shao, Qingyao Li et al.2026 · 0 citationsarXiv
Holder Policy Optimisation2605.12058v2 · Yuxiang Chen, Dingli Liang, Yihang Chen et al.2026 · 0 citationsarXiv
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents2605.09915v1 · Rong Shan, Te Gao, Hang Zheng et al.2026 · 0 citationsarXiv
Career total: at least 699 works. 422 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.