SkillOpt: Executive Strategy for Self-Evolving Agent Skills

• URL: http://arxiv.org/abs/2605.23904v2
• Date: Mon, 25 May 2026 17:58:16 GMT
• Title: SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• Abstract summary: 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.
• Score: 39.94802218531371
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt is best or tied on all 52 evaluated (model, benchmark, harness) cells and beats every per-cell competitor among human, one-shot LLM, Trace2Skill, TextGrad, GEPA, and EvoSkill skills. On GPT-5.5 it lifts the average no-skill accuracy by +23.5 points in direct chat, by +24.8 inside the Codex agentic loop, and by +19.1 inside Claude Code. Transfer experiments further show that optimized skill artifacts retain value when moved across model scales, between Codex and Claude Code execution environments, and to a nearby math benchmark without further optimization. Code: https://aka.ms/skillopt

Related papers

• COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization [55.60171725587438]
  Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience.<n>Existing skill optimization methods often rely on costly execution-based evaluation and substantial task data.<n>We introduce textbfCOBRA-Skills, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space.
  arXiv  Detail & Related papers  (2026-09-10T15:12:24Z)
• 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)
• Write, Execute, Refine: From Skill Followers to Skill Optimizers via Reinforcement Learning from Execution Feedback [52.78692582507693]
  Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill.<n>We study how to organize execution experience from intermediate skills into training states for an executor.
  arXiv  Detail & Related papers  (2026-08-18T09:52:48Z)
• 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)
• SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories [21.45159075534644]
  We propose SkillAdaptor, a training-free step-level skill adaptation framework with explicit failure attribution.<n>We evaluate it on WebShop, PinchBench, and Claw-Eval with Kimi-K2.5, GLM-5, and GPT-5.2.
  arXiv  Detail & Related papers  (2026-05-31T16:00:10Z)
• SkillEvolver: Skill Learning as a Meta-Skill [46.52001686198623]
  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.
  arXiv  Detail & Related papers  (2026-05-11T12:58:25Z)
• Skill-R1: Agent Skill Evolution via Reinforcement Learning [84.35984979949502]
  Skill-R1 is a reinforcement learning framework for instance-level recurrent skill optimization from verifiable rewards.<n>It preserves black-box compatibility with both open- and closed-source models while making adaptation substantially cheaper than model-level updates.
  arXiv  Detail & Related papers  (2026-05-10T06:19:15Z)
• 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)
• SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents [6.293920920196533]
  SkillLens is a hierarchical skill-evolution framework that organizes skills into a four-layer graph of policies, strategies, procedures, and primitives.<n>It retrieves semantically relevant skill seeds, expands them through degree-corrected random walk over the skill graph, and then uses a verifier to decide whether each visited unit should be accepted, decomposed, rewritten, or skipped.<n>Across MuLocbench and ALFWorld, SkillLens consistently improves over strong skill-based baselines.
  arXiv  Detail & Related papers  (2026-05-08T18:48:04Z)
• BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning [34.60596020541521]
  We present BadSkill, a backdoor attack formulation that targets model-in-skill threat surface.<n>In BadSkill, an adversary publishes a seemingly benign skill whose embedded model is backdoor-fine-tuned to activate a hidden payload.<n>Our benchmark spans 13 skills, including 8 triggered tasks and 5 non-trigger control skills, with a combined main evaluation set of 571 negative-class queries and 396 trigger-aligned queries.<n>BadSkill achieves up to 99.5% average attack success rate (ASR) across the eight triggered skills while maintaining strong benign-side accuracy on negative-class queries.
  arXiv  Detail & Related papers  (2026-04-10T14:48:29Z)
• 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)
• EffiSkill: Agent Skill Based Automated Code Efficiency Optimization [18.68243664364758]
  EffiSkill is a framework for code-efficiency optimization that builds a portable optimization toolbox for LLM-based agents.<n>EffiSkill adopts a two-stage design: Stage I mines Operator and Meta Skills from large-scale slow/fast program pairs to build a skill library.<n>Stage II applies this library to unseen programs through execution-free diagnosis, skill retrieval, plan composition, and candidate generation.
  arXiv  Detail & Related papers  (2026-03-29T20:09:57Z)
• MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild [74.7263562191605]
  Large language model (LLM) agents are increasingly used for complex tasks.<n>Existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining.<n>We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills.
  arXiv  Detail & Related papers  (2026-03-17T22:30:30Z)
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems [6.319876096746374]
  We introduce textbfEvoSkill, a self-evolving framework that automatically discovers and refines agent skills.<n>EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders.<n>We evaluate EvoSkill on two benchmarks: OfficeQA, a grounded reasoning benchmark over U.S. Treasury data, and SealQA, a noisy retrieval benchmark.
  arXiv  Detail & Related papers  (2026-03-03T09:07:22Z)

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.