10 papers
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Yu Wang, Yi-Kai Zhang, Wentao Shi +8
Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR)…
Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning
Ke Xu, Yuhao Wang, Ziyang Cheng +3
Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often sparse, temporally dispersed, and distributed across both audio and visual streams…
Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
Yuxin Chen, Xiaodong Cai, Junfeng Fang +9
Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite stron…
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Sirui Chen, Lei Xu, Yuying Zhao +6
Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewar…
MemGym: a Long-Horizon Memory Environment for LLM Agents
Wujiang Xu, Yu Wang, Kai Mei +8
Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-…
Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
Chongrui Ye, Yuxiang Liu, Yu Wang +5
Language agents increasingly operate over streams of related tasks, yet existing memory systems struggle to convert accumulated experience into reusable knowledge. Retrieval-augmen…