SkillEvolver: Skill Learning as a Meta-Skill

• URL: http://arxiv.org/abs/2605.10500v1
• Date: Mon, 11 May 2026 12:58:25 GMT
• Title: SkillEvolver: Skill Learning as a Meta-Skill
• Abstract summary: We propose textbfSkillEvolver, a lightweight, plug-and-play solution for online skill learning.<n>The learning target of SkillEvolver is the skill's prose and code, not model weights.<n>Unlike trace-distillation, the meta-skill refines only after deploying the learnt skill.
• Score: 46.52001686198623
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a lightweight, plug-and-play solution for online skill learning, in which a single meta-skill iteratively authors, deploys, and refines domain-specific skills. The learning target of SkillEvolver is the skill's prose and code, not model weights, so that the resulting artifact drops into any agent without retraining; and the meta-skill itself is just another skill, loaded through the same interface by any protocol-compliant CLI-agent. Unlike trace-distillation, the meta-skill refines only after deploying the learnt skill, such that the learning signal comes from failures another agent encounters while using it -- not from exploratory traces alone. Refinement iterations are governed by a fresh-agent overfit audit that catches possible leakage as well as deployed-skill-specific failures, including the silent-bypass mode in which a skill appears valid in content but is never invoked at runtime. On $83$ SkillsBench tasks spanning $15^{+}$ domains, SkillEvolver reaches $56.8\%$ accuracy versus $43.6\%$ for curated human skills and $29.9\%$ for the no-skill baseline; on three GPU kernel optimization tasks from KernelBench, it also raises mean speedup from $1.16$ to $1.51$ on average.

Related papers

• CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution [12.48020149385294]
  CoSkill is a unified multi-agent RL framework that recasts the static meta-skill workflow as a learnable Meta-Skill Agent.<n>By modeling the Reasoning and Meta-Skill Agents as a cooperative team sharing a single backbone, CoSkill enables end-to-end co-adaptation.
  arXiv  Detail & Related papers  (2026-09-04T08:25:30Z)
• Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills [86.15447717549154]
  We present DisCo, a skill-powered research agent that creates skills and uses them during research.<n>We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work.
  arXiv  Detail & Related papers  (2026-09-02T15:49:41Z)
• When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents [62.10623192614306]
  Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents.<n>We propose textbfBoundary-Aware Skill Memory (BASM), which augments each skill with explicit boundary fields.<n>BASM consistently outperforms success-distilled skill-memory baselines.
  arXiv  Detail & Related papers  (2026-08-23T10:16:06Z)
• MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution [24.78476085778134]
  Self-improving agents address this by rewriting their own skill files from execution traces, yielding meaningful gains on challenging benchmarks.<n>We introduce MetaSkill-Evolve, a two-timescale framework that makes agentic skill improvement recursive.<n>Task skills evolve on a fast loop while the meta-skill evolves on a slower one under the same pipeline applied to itself.<n>With all five pipeline agents sharing a single frozen backbone, MetaSkill-Evolve outperforms no-skill, static-skill, and single-level evolution baselines.
  arXiv  Detail & Related papers  (2026-07-06T16:40:23Z)
• AIP: A Graph Representation for Learning and Governing Agent Skills [1.1458853556386797]
  Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-derive how to act in every session.<n>This imposes two compounding costs: reduced reliability on implementation-heavy tasks, and difficulty in skill creation and improvement.<n>The Agent Instruction Protocol (AIP) addresses both by modeling a skill as a directed execution graph.<n>A compiler meta-skill translates existing human-written skills into this form.
  arXiv  Detail & Related papers  (2026-06-03T12:02:49Z)
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills [39.94802218531371]
  SkillOpt is a controllable text-space for agent skills.<n>A separate model turns scored rollouts into bounded add/delete/replace edits on a single skill document.<n>A learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable.
  arXiv  Detail & Related papers  (2026-05-22T17:59:50Z)
• SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces [6.384302247811717]
  In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a runtime task.<n>We find that this execution paradigm introduces two major sources of redundancy: irrelevant context injection and repeated skill-specific reasoning and planning.<n>We propose SkillSmith, a boundary-first compiler-runtime framework that compiles skill packages offline into minimal executable interfaces.
  arXiv  Detail & Related papers  (2026-05-12T09:25:25Z)
• SkillGen: Verified Inference-Time Agent Skill Synthesis [60.927977774369516]
  SkillGen is a framework that synthesizes a single auditable skill from trajectories generated by a base agent.<n>It identifies reusable success patterns, recurring failure modes, and behaviors that appear in nearby successes but are missing from failures.<n>A key novelty in SkillGen is that we model agent skills as interventions to empirically verify the net effect of skills on the overall performance.
  arXiv  Detail & Related papers  (2026-05-09T19:24:11Z)
• SkillOS: Learning Skill Curation for Self-Evolving Agents [67.94374107466957]
  We propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents.<n>SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience.<n>We show that SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-05-07T17:31:50Z)
• Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills [27.93279540484981]
  Graph of Skills (GoS) is an inference-time structural retrieval layer for large skill libraries.<n>GoS improves average reward by 43.6% over the vanilla full skill-loading baseline.<n>GoS consistently outperforms both vanilla skills loading and simple vector retrieval.
  arXiv  Detail & Related papers  (2026-04-07T02:09:11Z)
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization [61.37478254738943]
  Inference-time skill augmentation is fundamentally limited.<n>We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization.<n>SKILL0 achieves substantial improvements over the standard RL baseline.
  arXiv  Detail & Related papers  (2026-04-02T17:03:05Z)
• EvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification [85.3692584167951]
  Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks.<n>A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts.<n>EvoSkills is a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages.
  arXiv  Detail & Related papers  (2026-04-02T06:43:20Z)
• SkillRouter: Skill Routing for LLM Agents at Scale [18.540967600258607]
  Given a user task, the system must identify relevant skills before downstream planning or execution.<n>Existing agent stacks often rely on progressive disclosure, exposing only skill names and descriptions while hiding the full implementation body.<n>We present Skill, a compact 1.2B full-text retrieve-and-rerank pipeline.
  arXiv  Detail & Related papers  (2026-03-23T18:23:59Z)
• SkillClone: Multi-Modal Clone Detection and Clone Propagation Analysis in the Agent Skill Ecosystem [16.221297353469957]
  We present SkillClone, the first multi-modal clone detection approach for agent skills.<n>On SkillClone-Bench, SkillClone achieves F1 of 0.939 with precision 0.952, outperforming flat TF-IDF.<n>Applying SkillClone to 20K skills reveals 258K clone pairs involving 75% of all skills, with 40% crossing author boundaries.
  arXiv  Detail & Related papers  (2026-03-23T18:17:17Z)
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks [61.89812116484928]
  Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time.<n>We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers.<n>We show curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain.<n>Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming.
  arXiv  Detail & Related papers  (2026-02-13T07:06:06Z)
• Skill-Based Reinforcement Learning with Intrinsic Reward Matching [77.34726150561087]
  We present Intrinsic Reward Matching (IRM), which unifies task-agnostic skill pretraining and task-aware finetuning. IRM enables us to utilize pretrained skills far more effectively than previous skill selection methods.
  arXiv  Detail & Related papers  (2022-10-14T00:04:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.