SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization

• URL: http://arxiv.org/abs/2606.06079v1
• Date: Thu, 04 Jun 2026 12:16:08 GMT
• Title: SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization
• Abstract summary: Agent skills are reusable strategies that guide agent reasoning and action.<n>Current skill construction methods treat the problem as one-shot extraction.<n>We introduce SkillComposer, a framework that decomposes skill construction into three learnable operations.
• Score: 99.18305770138677
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agent skills, which consist of reusable strategies that guide agent reasoning and action, have shown strong potential for improving model capability at inference time. However, current skill construction methods treat the problem as one-shot extraction, overlooking a fundamental tension: a skill tailored to the specific task fails to transfer, while the abstracted skill often provides insufficient guidance. We attribute this fragility to the absence of explicit mechanisms for skill specification and generalization. To address this gap, we introduce SkillComposer, a framework that decomposes skill construction into three learnable operations: create, improve, and merge. Trained via systematic rejection sampling recipe, SkillComposer enables language models to self-evolve skills at inference time and supports three deployment modes: offline for building generalized libraries, online for task-specific refinement, and hybrid for combining both. Comprehensive experiments on $τ^2$-Bench, LiveCodeBench v6, and AppWorld show that SkillComposer consistently outperforms baselines. Our SkillComposer-4B improves a 27B executor by up to +4.5 on agent tasks and +3.4 on code tasks, while generalizing across domains and task types unseen during training. Analysis reveals that merge and improve address orthogonal quality dimensions and that skill composition is a transferable meta-ability, providing a practical recipe for skill-augmented inference.

Related papers

• SkillAligner: Treating Retrieved Skills as Adaptable Drafts at Execution Time [14.34844805305673]
  General-purpose skills promise reusable procedural knowledge for language agents.<n>But semantic relevance does not guarantee execution utility.<n>We propose SkillAligner, a training-free execution-time skill adaptation framework.
  arXiv  Detail & Related papers  (2026-08-07T07:05:53Z)
• ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities? [42.712923465058786]
  We introduce ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning.<n>We show that sequential execution generally improves performance, but the gains vary substantially across models and domains.<n>We further find that less capable models tend to accumulate larger, more fragmented collections of task-specific skills.
  arXiv  Detail & Related papers  (2026-08-04T16:15:02Z)
• 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)
• Generative Skill Composition for LLM Agents [58.47191648555256]
  LLM agents benefit from skills for solving complex tasks.<n>As skill libraries grow, selecting an appropriate skill composition has emerged as a central bottleneck.<n>We propose SkillComposer, which instantiates structured skill composition as task-conditioned skill sequence prediction.
  arXiv  Detail & Related papers  (2026-06-30T17:53:09Z)
• SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents [38.2600862878199]
  Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is constrained by a lack of systematic skill construction, accumulation, and transfer.<n>We propose SkillPyramid, a skill consolidation framework that reuses existing skill experience for broader task generalization.<n>We show that SkillPyramid substantially increases the average reward by 38.0% and reduces execution steps by 27.7%.
  arXiv  Detail & Related papers  (2026-06-02T14:14:27Z)
• SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems [36.96247516261787]
  SkillSmith is a synergy-aware skill-tool co-evolution framework.<n>It allows tools to be wrapped, edited, composed, split, or retired when skill evolution identifies a reusable capability gap.<n>It records anti-patterns, including failure signatures, causal attributions, and remedies, to accelerate diagnosis and veto proposals that repeat known mistakes.
  arXiv  Detail & Related papers  (2026-05-31T16:01:19Z)
• 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)
• 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)
• SkillX: Automatically Constructing Skill Knowledge Bases for Agents [27.56549031749266]
  SkillX is a fully automated framework for constructing a plug-and-play skill knowledge base.<n>It operates through a fully automated pipeline built on three synergistic innovations.<n> Experiments show that SkillKB consistently improves task success and execution efficiency when plugged into weaker base agents.
  arXiv  Detail & Related papers  (2026-04-06T16:09:33Z)
• 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)
• Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation [32.86306309089796]
  Uni-Skill is a skill-centric framework that supports skill-aware planning.<n>Uni-Skill requests for new skill implementations when existing ones are insufficient.<n>Skill is a VerbNet-inspired repository derived from large-scale unstructured robotic videos.
  arXiv  Detail & Related papers  (2026-03-03T05:49:37Z)
• SkillCraft: Can LLM Agents Learn to Use Tools Skillfully? [67.69996753743129]
  We introduce SkillCraft, a benchmark explicitly stress-test agent ability to form and reuse higher-level tool compositions.<n> SkillCraft features realistic, highly compositional tool-use scenarios with difficulty scaled along both quantitative and structural dimensions.<n>We propose a lightweight evaluation protocol that enables agents to auto-compose atomic tools into executable Skills, cache and reuse them inside and across tasks.
  arXiv  Detail & Related papers  (2026-02-28T15:44:31Z)

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.