SkillOS: Learning Skill Curation for Self-Evolving Agents

• URL: http://arxiv.org/abs/2605.06614v1
• Date: Thu, 07 May 2026 17:31:50 GMT
• Title: SkillOS: Learning Skill Curation for Self-Evolving Agents
• Abstract summary: 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.
• Score: 67.94374107466957
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for self-evolution, where high-quality skill curation serves as the key bottleneck. Existing approaches either rely on manual skill curation, prescribe heuristic skill operations, or train for short-horizon skill operations. However, they still struggle to learn complex long-term curation policies from indirect and delayed feedback. To tackle this challenge, we propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents. SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience. To provide learning signals for curation, we design composite rewards and train on grouped task streams based on skill-relevant task dependencies, where earlier trajectories update the SkillRepo, and later related tasks evaluate these updates. Across multi-turn agentic tasks and single-turn reasoning tasks, SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency, with the learned skill curator generalizing across different executor backbones and task domains. Further analyses show that the learned curator produces more targeted skill use, while the skills in SkillRepo evolve into more richly structured Markdown files that encode higher-level meta-skills over time.

Related papers

• SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents [17.565432600589414]
  Large language model (LLM) agents are trained with reinforcement learning (RL) for complex decision-making tasks.<n>Recent skill-based approaches, such as SkillRL, attempt to address this issue by extracting skills from raw trajectories.<n>We propose SkillForge, a framework for continuous skill evolution that enables skills to be verified and refined through environment interaction.
  arXiv  Detail & Related papers  (2026-08-25T15:52:10Z)
• SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution [39.74364990208475]
  Large language model agents often encounter related yet distinct tasks that share reusable solution patterns.<n>We introduce SkillRise, a unified reinforcement learning framework for learning skills across tasks.
  arXiv  Detail & Related papers  (2026-07-29T11:26:33Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation [14.16890033854702]
  Large language model (LLM) agents rely on reusable skills to solve complex tasks.<n>Existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement.<n>We propose MUSE-Autoskill Agent, a skill-centric agent framework that lets agents continuously improve their task-solving capability.
  arXiv  Detail & Related papers  (2026-05-26T17:59:19Z)
• CODESKILL: Learning Self-Evolving Skills for Coding Agents [13.599750520978988]
  Coding agents produce rich trajectories while solving software-engineering tasks.<n>To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.<n>We propose CODESKILL, an LLM-based framework that reformulates skill extraction and skill-bank maintenance as a learnable management policy.
  arXiv  Detail & Related papers  (2026-05-25T05:12:49Z)
• 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)
• SkillMaster: Toward Autonomous Skill Mastery in LLM Agents [27.651128308229378]
  We propose SkillMaster, a training framework that teaches agents to create new skills, refine existing skills, and select accumulated skills during task solving.<n>First, we train agents through trajectory-informed skill review, teaching agents to propose, update, or retain skills based on evidence from completed episodes.<n>Second, each candidate skill edit is designed to be evaluated by its counterfactual utility on related probe tasks, providing a direct learning signal for training skill-editing decisions.<n>Third, we introduce DualAdv-GRPO, which separately estimates advantages for task-solving actions and skill-editing decisions, stabilizing joint training across task solving and
  arXiv  Detail & Related papers  (2026-05-09T05:03:00Z)
• From Context to Skills: Can Language Models Learn from Context Skillfully? [56.5857437218136]
  Ctx2Skill is a self-evolving framework that autonomously discovers, refines, and selects context-specific skills.<n>It can be plugged into any language model to obtain better context learning capability.
  arXiv  Detail & Related papers  (2026-04-30T09:53:15Z)
• 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)
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning [83.98129545309277]
  We propose SkillRL, a framework that bridges the gap between raw experience and policy improvement.<n>Our approach introduces an experience-based distillation mechanism to build a hierarchical skill library SkillBank.<n> Experimental results on ALF, WebShop and seven search-augmented tasks demonstrate that SkillRL achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-09T03:17:17Z)
• Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning [39.991887534269445]
  Disentangled Unsupervised Skill Discovery (DUSDi) is a method for learning disentangled skills that can be efficiently reused to solve downstream tasks. DUSDi decomposes skills into disentangled components, where each skill component only affects one factor of the state space. DUSDi successfully learns disentangled skills, and significantly outperforms previous skill discovery methods when it comes to applying the learned skills to solve downstream tasks.
  arXiv  Detail & Related papers  (2024-10-15T04:13:20Z)
• Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance [66.615355754712]
  BOSS learns to accomplish new tasks by performing "skill bootstrapping" We demonstrate through experiments in realistic household environments that agents trained with our LLM-guided bootstrapping procedure outperform those trained with naive bootstrapping.
  arXiv  Detail & Related papers  (2023-10-16T02:43:47Z)
• Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning [27.69559938165733]
  Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. We investigate how skills can be incorporated into the training of reinforcement learning (RL) agents in complex environments. Our experiments show that learning with a prior knowledge of useful skills can significantly improve the performance of agents on complex problems.
  arXiv  Detail & Related papers  (2022-07-23T19:23:29Z)
• Accelerating Reinforcement Learning with Learned Skill Priors [20.268358783821487]
  Most modern reinforcement learning approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on prior tasks to the new task. We show that learned skill priors are essential for effective skill transfer from rich datasets.
  arXiv  Detail & Related papers  (2020-10-22T17:59:51Z)

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.