14 papers
HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
Haoyun Tang, Haodong Cui, Keyao Xu +2
World models enable model-based planning through learned latent dynamics, but imagined rollouts become unstable as the planning horizon grows or the dynamics distribution shifts. W…
AcademiClaw: When Students Set Challenges for AI Agents
Junjie Yu, Pengrui Lu, Weiye Si +75
Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We intro…
MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
Yin Zhang, Jiaxuan Zhao, Zonghan Wu +5
Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning…
SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication
Ruijia Zhang, Xinyan Zhao, Ruixiang Wang +5
LLM-based multi-agent systems exhibit strong collaborative capabilities but often suffer from redundant communication and excessive token overhead. Existing methods typically enhan…
LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
Guibin Zhang, Fanci Meng, Guancheng Wan +5
Test-time Scaling (TTS) has been demonstrated to significantly enhance the reasoning capabilities of Large Language Models (LLMs) during the inference phase without altering model…
AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
Guibin Zhang, Junhao Wang, Junjie Chen +3
Large Language Model (LLM)-based agentic systems, often comprising multiple models, complex tool invocations, and orchestration protocols, substantially outperform monolithic agent…