6 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…
RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation
Zongzheng Zhang, Chenghao Yue, Haobo Xu +5
Robotic chemists promise to both liberate human experts from repetitive tasks and accelerate scientific discovery, yet remain in their infancy. Chemical experiments involve long-ho…
BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?
Zongmeng Zhang, Jinhua Zhu, Wengang Zhou +3
Dense retrieval, which aims to encode the semantic information of arbitrary text into dense vector representations or embeddings, has emerged as an effective and efficient paradigm…
Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
Zongmeng Zhang, Yufeng Shi, Jinhua Zhu +4
Trustworthiness is an essential prerequisite for the real-world application of large language models. In this paper, we focus on the trustworthiness of language models with respect…