Agents
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
arXiv:2604.09297v1 Announce Type: cross Abstract: Agent skills provide modular, task-specific guidance for LLM- based coding agents, but manually tuning skill bundles to balance success rate, cost, an
arXiv:2604.09297v1 Announce Type: cross Abstract: 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.
Related
- SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
- Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects
- How Much LLM Does a Self-Revising Agent Actually Need?
- TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design
Source: arXiv cs.AI | 2026-04-13