[2603.02766] EvoSkill: Automated Skill Discovery for Multi-Agent Systems

Computer Science > Artificial Intelligence arXiv:2603.02766 (cs) [Submitted on 3 Mar 2026] Title:EvoSkill: Automated Skill Discovery for Multi-Agent Systems Authors:Salaheddin Alzubi, Noah Provenzano, Jaydon Bingham, Weiyuan Chen, Tu Vu View a PDF of the paper titled EvoSkill: Automated Skill Discovery for Multi-Agent Systems, by Salaheddin Alzubi and 4 other authors View PDF HTML (experimental) Abstract:Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable workflows, and code, that augment agents with domain-specific capabilities. Most skills today are hand-crafted, and existing evolutionary approaches optimize low-level artifacts (e.g. prompts \& code) that are tightly coupled to specific models and tasks. We introduce \textbf{EvoSkill}, a self-evolving framework that automatically discovers and refines agent skills through iterative failure analysis. EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders. A Pareto frontier of agent programs governs selection, retaining only skills that improve held-out validation performance while the underlying model remains frozen. We evaluate EvoSkill on two benchmarks: OfficeQA, a grounded reasoning benchmark over U.S.\ Treasury data, where it improves exact-mat...