SkillX: 为智能体自动构建技能知识库
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
AI总结：
SkillX通过多级技能设计、迭代技能精炼和探索性技能扩展，构建可复用的技能知识库，提升智能体在长周期任务中的表现和泛化能力。
摘要：
从经验中学习对于构建有能力的大语言模型（LLM）智能体至关重要，但现有的自我进化范式效率低下：智能体孤立学习，从有限经验中反复发现相似行为，导致冗余探索和泛化能力差。为解决此问题，我们提出了SkillX，一个完全自动化的框架，用于构建可跨智能体和环境复用的插拔式技能知识库。SkillX通过一个完全自动化的流程，基于三个协同创新：（i）多级技能设计，将原始轨迹提炼为战略计划、功能技能和原子技能的三级体系；（ii）迭代技能精炼，根据执行反馈自动修订技能以持续提升库质量；（iii）探索性技能扩展，主动生成并验证新技能以扩展覆盖范围。使用强基础智能体（GLM-4.6），我们自动构建了可复用的技能库，并在具有挑战性的长周期、用户交互基准上评估其可转移性，包括AppWorld、BFCL-v3和τ²-Bench。实验表明，当SkillKB插入到较弱的基础智能体中时，任务成功率和执行效率持续提高，突显了结构化、分层经验表示对于可泛化的智能体学习的重要性。我们的代码将在不久后公开发布于https://github.com/zjunlp/SkillX。
英文摘要：
Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited experience, resulting in redundant exploration and poor generalization. To address this problem, we propose SkillX, a fully automated framework for constructing a \textbf{plug-and-play skill knowledge base} that can be reused across agents and environments. SkillX operates through a fully automated pipeline built on three synergistic innovations: \textit{(i) Multi-Level Skills Design}, which distills raw trajectories into three-tiered hierarchy of strategic plans, functional skills, and atomic skills; \textit{(ii) Iterative Skills Refinement}, which automatically revises skills based on execution feedback to continuously improve library quality; and \textit{(iii) Exploratory Skills Expansion}, which proactively generates and validates novel skills to expand coverage beyond seed training data. Using a strong backbone agent (GLM-4.6), we automatically build a reusable skill library and evaluate its transferability on challenging long-horizon, user-interactive benchmarks, including AppWorld, BFCL-v3, and $τ^2$-Bench. Experiments show that SkillKB consistently improves task success and execution efficiency when plugged into weaker base agents, highlighting the importance of structured, hierarchical experience representations for generalizable agent learning. Our code will be publicly available soon at https://github.com/zjunlp/SkillX.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
