skill-self-play-pushing-the-frontier-of-llm-capability-with-co-evolving-skills-a33f51ef·1 events·first seen Aliases: Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Researchers introduce Skill Self-Play (Skill-SP), a reinforcement learning framework that addresses the diversity-vs-verifiability dilemma in LLM self-evolution by using agent skills as a middle ground. The system comprises a proposer, solver, and dynamic skill controller that co-evolve in a continuous loop: the proposer generates tasks conditioned on sampled skills, the solver explores solutions, and the skill controller updates an expanding skill library based on execution feedback. Evaluations on tool-use and reasoning benchmarks show consistent performance gains on capable backbones and recovery for initially misaligned models. Code is released under the Qwen-Applications GitHub organization, suggesting Alibaba/Qwen team involvement.