EvoSkill-S1: Evolving Reusable Skills with Genetic-Inspired Operators
Reusable skills allow language-model agents to accumulate and reuse problem-solving experience. However, most existing methods improve a skill bank only indirectly through rollout-driven accumulation and heuristic reflection, often resulting in shallow and weakly controlled updates. We present EvoSkill-S1, an RL-driven framework that instead treats reusable skills themselves as the direct objects of evolution. Given hard-negative failures, EvoSkill-S1 selects parent skills and transforms them into candidate child skills through five genetic-inspired operators: revision, cross-revision, mutation, dual-reflection, and crossover. Downstream task rewards train the skill evolver to generate more effective child skills, while evaluator-guided write-back selectively retains beneficial updates. Complementary Skill Bank Fusion consolidates operator-specific banks to exploit their distinct recovery patterns, while a Procedural Skill Interface supports transfer to unseen problems. Across all reported math and code benchmarks, EvoSkill-S1 improves the corresponding initialized skill banks under both Qwen and GPT-family solvers, with relative gains of up to 12.39%. Compared with the strongest external baseline without direct skill evolution, the largest relative improvement reaches 20.39%.
Authors
- Boliang Liu (ORCID: https://orcid.org/0009-0003-6919-830X)
- Wenxuan Ye
- Jinhe Bi (ORCID: https://orcid.org/0000-0002-9589-251X)
- Yinuo Lu
- Sikuan Yan
- Aniri
- Xuebing Zhou
- Hinrich Sch{ü}tze
- Shuning Wang
- Jiqiang Li
- Yujun Wang
- S{ö}ren Pirk
- Yunpu Ma
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.48550/arxiv.2611.22610
- Primary Topic
- Evolutionary Algorithms and Applications
- Type
- preprint