Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
- URL: http://arxiv.org/abs/2607.22529v1
- Date: Fri, 24 Jul 2026 17:59:22 GMT
- Title: Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
- Abstract summary: 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.
- Score: 53.15216425100295
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task diversity and verification reliability: environment-bound methods obtain precise feedback but confine learning to narrow domains, while open-ended self-generation broadens the task space but lacks reliable verification, allowing misleading rewards to pollute the training loop. We identify agent skills as a powerful middle ground to reconcile this tension: each skill ensures deep, verifiable execution in a specific scenario, while dynamic routing across skills maintains open-ended task variety. Leveraging this insight, we introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a dynamic skill controller. Orchestrated via a reinforcement learning loop, these components co-evolve in a continuous self-play loop: 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. This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration. Empirical evaluations on tool-use and reasoning benchmarks demonstrate that Skill-SP, serving as a robust evolution engine, consistently pushes the performance ceiling of competent backbones while catalyzing striking turnarounds for initially misaligned models. Our code is available at https://github.com/Qwen-Applications/skill-self-play.
Related papers
- Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents [67.97365535829098]
Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.<n>We propose Evo-Harness, which distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation.<n>Our analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly.
arXiv Detail & Related papers (2026-08-15T06:43:56Z) - Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning [23.79611349616925]
Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks.<n>Self-evolving skill systems have been developed to automatically construct and update skills from execution trajectories.<n>We propose Trajectory Backdoor Attack (TBA), a query-only attack that steers a trusted skill-evolution pipeline toward producing a backdoored skill.
arXiv Detail & Related papers (2026-08-08T19:31:19Z) - Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning [60.37693496953694]
Embodied Continual Learning (ECL) aims to enable robots to continually acquire new manipulation tasks.<n>ECL suffers from more severe catastrophic forgetting.<n>Key challenge in ECL lies in structured skill reuse across continually evolving tasks.
arXiv Detail & Related papers (2026-06-14T09:02:49Z) - SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization [99.18305770138677]
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.
arXiv Detail & Related papers (2026-06-04T12:16:08Z) - Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents [32.49699221723716]
Lifelong learning is essential for Large Language Model (LLM) agents operating in dynamic, interactive environments.<n>We propose Skill-enhanced Test-Time Co-Evolution (textttLifeSkill), a two-stage reinforcement learning framework for Online Lifelong Learning Agents.
arXiv Detail & Related papers (2026-06-03T12:38:57Z) - SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration [40.79922760459963]
SkillFlow is a flow-based framework that takes a trainable Supervisor as the agent and a structured environment with dynamic skill orchestration.<n>Building on these flow diagnostics, a skill evolution mechanism determines when to evolve, what skills to create or prune, and where decision gaps lie.
arXiv Detail & Related papers (2026-05-13T20:14:44Z) - 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)
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.