7 papers
Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
Hao Wu, Shoucheng Song, Chang Yao +4
Multi-Agent Debate (MAD) improves the reasoning performance of Large Language Models (LLMs) through multi-round interaction. However, LLMs in MAD are highly susceptible to blind co…
MinInter: Minimizing Trajectory Interpolation During Data Augmentation for Imitation Learning
Qingyang Wang, Xingang Liu, Changwei Yao +4
Imitation learning enables robots to acquire complex manipulation skills from demonstrations, but its effectiveness is limited by the cost of collecting high-quality data. Trajecto…
Reward Evolution with Graph-of-Thoughts: A Bi-Level Language Model Framework for Reinforcement Learning
Changwei Yao, Xinzi Liu, Chen Li +1
Designing effective reward functions remains a major challenge in reinforcement learning (RL), often requiring considerable human expertise and iterative refinement. Recent advance…
LLM-assisted Semantic Option Discovery for Facilitating Adaptive Deep Reinforcement Learning
Chang Yao, Jinghui Qin, Kebing Jin +1
Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficie…
Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution
Hao Wu, Shoucheng Song, Chang Yao +4
In multi-agent systems, explicit cognition of teammates' decision logic serves as a critical factor in facilitating coordination. Communication (i.e., ``\textit{Tell}'') can assist…
From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination
Chang Yao, Youfang Lin, Shoucheng Song +4
Continual Multi-Agent Reinforcement Learning (Co-MARL) requires agents to address catastrophic forgetting issues while learning new coordination policies with the dynamics team. In…