Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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typically expand these banks in an append-only fashion, continuously adding new skills without removing redundant, outdated, or harmful ones, resulting in inefficient and poorly curated repositories.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typically expand these banks in an append-only fashion, continuously adding new skills without removing redundant, outdated, or harmful ones, resulting in inefficient and poorly curated repositories.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 |