4 papers
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Zhuoyun Yu, Xin Xie, Wuguannan Yao +4
Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill adaptation pipelines usually u…
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Chenxi Wang, Zhuoyun Yu, Xin Xie +8
Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, r…
SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval
Xin Xie, Dongyun Xue, Wuguannan Yao +5
LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inf…
Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning
Tao Li, Juan Guevara, Xinhong Xie +1
Offline reinforcement learning (RL) suffers from the distribution shift between the offline dataset and the online environment. In multi-agent RL (MARL), this distribution shift ma…