SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
This addresses the challenge of balancing success rate, cost, and runtime for software engineering agents, though it is incremental as it builds on existing optimization methods.
The paper tackles the problem of manually tuning skill bundles for LLM-based coding agents by introducing SkillMOO, a multi-objective optimization framework that automatically evolves skill bundles, resulting in up to 131% improvement in pass rate and up to 32% reduction in cost on software engineering tasks.
Agent skills provide modular, task-specific guidance for LLM- based coding agents, but manually tuning skill bundles to balance success rate, cost, and runtime is expensive and fragile. We present SkillMOO, a multi-objective optimization framework that automatically evolves skill bundles using LLM-proposed edits and NSGA-II survivor selection: a solver agent evaluates candidate skill bundles on coding tasks and an optimizer agent proposes bundle edits based on failure analysis. On three SkillsBench software engineering tasks, SkillMOO improves pass rate by up to 131% while reducing cost up to 32% relative to the best baseline per task at low optimization overhead. Pattern analysis reveals pruning and substitution as primary drivers of improvement, suggesting effective bundles favor minimal, focused content over accumulated instructions.