SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911691505139712 |
|---|---|
| author | Gong, Jingzhi Gu, Ruizhen Fei, Zhiwei Cao, Yazhuo Twist, Lukas Geiger, Alina Han, Shuo Sobania, Dominik Sarro, Federica Zhang, Jie M. |
| author_facet | Gong, Jingzhi Gu, Ruizhen Fei, Zhiwei Cao, Yazhuo Twist, Lukas Geiger, Alina Han, Shuo Sobania, Dominik Sarro, Federica Zhang, Jie M. |
| contents | Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE tasks, SkillMOO achieves the top pass rate rank on 11 of 12 non-zero-pass tasks while achieving cost reductions of up to 31.7% over static bundles, with pass rate gains up to 21 percentage points. Analysis of 38 skill edits shows that pruning and substitution dominate successful operations, offering actionable principles for skill bundle design. Thereby, the current practice of deploying skills without cost-aware validation leaves better skill configurations unexplored, motivating a new class of cost-aware, search-based skill engineering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09297 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering Gong, Jingzhi Gu, Ruizhen Fei, Zhiwei Cao, Yazhuo Twist, Lukas Geiger, Alina Han, Shuo Sobania, Dominik Sarro, Federica Zhang, Jie M. Software Engineering Artificial Intelligence Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE tasks, SkillMOO achieves the top pass rate rank on 11 of 12 non-zero-pass tasks while achieving cost reductions of up to 31.7% over static bundles, with pass rate gains up to 21 percentage points. Analysis of 38 skill edits shows that pruning and substitution dominate successful operations, offering actionable principles for skill bundle design. Thereby, the current practice of deploying skills without cost-aware validation leaves better skill configurations unexplored, motivating a new class of cost-aware, search-based skill engineering. |
| title | SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2604.09297 |