{"work":{"id":"509f2c7c-7ee4-4b35-aa68-a3db839ad987","openalex_id":"https://openalex.org/W7148785316","doi":"10.48550/arxiv.2604.01687","arxiv_id":"2604.01687","raw_key":null,"title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification","authors":null,"authors_text":"Hanrong Zhang, Shicheng Fan, Henry Peng Zou, Yankai Chen, Zhenting Wang, Jiayu Zhou, Chengze Li, Wei-Chieh Huang, Yifei Yao, Kening Zheng","year":2026,"venue":"cs.AI","abstract":"Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts. Currently, skill generation is not only label-intensive due to manual authoring, but also may suffer from human--machine cognitive misalignment, which can lead to degraded agent performance, as evidenced by evaluations on SkillsBench. Therefore, we aim to enable agents to autonomously generate skills. However, existing self-evolving methods designed for tools cannot be directly applied to skills due to their increased complexity. To address these issues, we propose CoEvoSkills, a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages. Specifically, CoEvoSkills couples a Skill Generator that iteratively refines skills with a Surrogate Verifier that co-evolves to provide informative and actionable feedback without access to ground-truth test content. On SkillsBench, CoEvoSkills achieves the highest pass rate among five baselines on both Claude Code and Codex, and also exhibits strong generalization capabilities to six additional LLMs.","external_url":"https://arxiv.org/abs/2604.01687","cited_by_count":0,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2604.01687","created_at":"2026-05-10T00:59:49.692201+00:00","updated_at":"2026-08-05T02:49:54.815029+00:00","title_quality_ok":true,"display_title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification","render_title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification"},"hub":{"state":{"work_id":"509f2c7c-7ee4-4b35-aa68-a3db839ad987","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":31,"external_cited_by_count":0,"distinct_field_count":8,"first_pith_cited_at":"2026-04-10T13:08:01+00:00","last_pith_cited_at":"2026-07-02T08:28:51+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-21T23:29:25.838426+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"dataset","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"unclear","n":1},{"context_polarity":"use_dataset","n":1},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}