一句话：提出 SkillMOO，将软件工程智能体技能包视为多目标搜索对象，用 LLM 编辑与 NSGA-II 联合优化通过率和推理成本。
现有编码智能体技能包多为静态手工资产，或仅按通过率进化，可能提高成功率却大幅增加 token 成本或引入误导。SkillMOO 将 SE 智能体技能包视为多目标搜索对象，用 LLM 提出编辑，并以 NSGA-II 在通过率和推理成本上做 Pareto 选择。在全部 16 个 SkillsBench SE 任务上，SkillMOO 在 12 个非零通过率任务中的 11 个取得最高通过率排名，相对静态技能包最多降本 31.7%，通过率最多提升 42 个百分点。38 次技能编辑分析显示，剪枝和替换是主要成功操作，为技能包设计提供可操作原则。
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 42 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 multi-objective search-based skill engineering.
@inproceedings{abs-2604-09297,
title = {SkillMOO: Multi-objective Optimization of Agent Skills for Software Engineering},
author = {Jingzhi Gong and Ruizhen Gu and Zhiwei Fei and Yazhuo Cao and Lukas Twist and Alina Geiger and Shuo Han and Dominik Sobania and Federica Sarro and Jie M. Zhang},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834550}
}