Saved in:
Bibliographic Details
Main Authors: Hu, Wentao, Chu, Zhendong, Zhang, Yiming, Wu, Junda, Jin, Ming, Zhao, Xiangyu, Shao, Yilei, Wang, Yanfeng, Wen, Qingsong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.29440
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910269072998400
author Hu, Wentao
Chu, Zhendong
Zhang, Yiming
Wu, Junda
Jin, Ming
Zhao, Xiangyu
Shao, Yilei
Wang, Yanfeng
Wen, Qingsong
author_facet Hu, Wentao
Chu, Zhendong
Zhang, Yiming
Wu, Junda
Jin, Ming
Zhao, Xiangyu
Shao, Yilei
Wang, Yanfeng
Wen, Qingsong
contents 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typically expand these banks in an append-only fashion, continuously adding new skills without removing redundant, outdated, or harmful ones, resulting in inefficient and poorly curated repositories.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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29440
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
Hu, Wentao
Chu, Zhendong
Zhang, Yiming
Wu, Junda
Jin, Ming
Zhao, Xiangyu
Shao, Yilei
Wang, Yanfeng
Wen, Qingsong
Computation and Language
Artificial Intelligence
Information Retrieval
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typically expand these banks in an append-only fashion, continuously adding new skills without removing redundant, outdated, or harmful ones, resulting in inefficient and poorly curated repositories.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.
title SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2605.29440