提出多目标优化框架，让大模型技能库更高效、多样且覆盖全面。
SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
- 用双层循环优化技能库，兼顾实用性、多样性和查询覆盖。
- 在两个公开数据集上验证，显著优于持续追加的旧方法。
- 适合构建可自我迭代的大模型智能体，提升长期决策能力。
检索增强型大模型智能体越来越依赖于经过精心整理的技能库——即一系列可复用的文本原则，用于指导复杂任务中的决策。现有方法通常以追加式方式扩展技能库，持续添加新技能而忽略冗余、过时或有害内容，导致资源浪费且管理低效。本文将技能库的维护问题建模为一个受约束的多目标优化问题：理想的技能库应具备实用性、内容多样性，并能良好覆盖查询分布。为此，我们提出 SkillBrew 框架，将技能库优化形式化为满足效用约束的帕累托感知优化问题，并通过双层‘提议-验证’机制求解。我们在两个公开基准上进行了评估，结果表明，将技能库视为需要系统性治理的对象，而非不断增长的追加日志，是实现自进化大模型智能体的关键一步。
原文摘要 · Abstract (English)
Retrieval-augmented LLM agents increasingly rely on curated skill banks: collections of reusable textual principles that guide decision making on complex tasks. Existing approaches typically expand these banks in an append-only fashion, continuously adding new skills without removing redundant, outdated, or harmful ones, resulting in inefficient and poorly curated repositories. In this paper, we formulate the skill bank curation as a constrained multi-objective problem: a desirable bank must be useful for the agent, diverse in its content, and provide good coverage of the query distribution. To this end, we introduce SkillBrew, a multi-objective curation framework that formalizes skill bank curation as Pareto-aware optimization under a utility constraint, and solves it via a bi-level propose-then-verify loop. We evaluate our approach on two public benchmarks. Our findings suggest that treating skill banks as objects of principled curation, rather than ever-growing append-only logs, is an important step toward building self-improving LLM agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。