AI自己跟自己玩，越玩越强
AI训练正从人工标注转向自我进化，但现有方法要么任务太窄（比如只会下棋），要么任务太广但没法验证对错（容易学歪）。这篇论文提出一个巧妙的中间方案：把能力拆成一个个“技能”（比如“用计算器”“查资料”），每个技能在特定场景下可验证，然后通过动态组合技能来生成无限多样的任务。三个AI角色——出题者、解题者、技能管理员——在强化学习循环中互相博弈：出题者根据当前技能库出难题，解题者尝试破解，管理员根据解题反馈更新技能库。这样既保证了任务多样性，又让每个任务有据可查。在工具使用和推理测试上，它让原本就强的模型更强，也让跑偏的模型扭回来。不是你明天能用上的，但展示了AI自我进化的一个靠谱方向。
📄 原文摘要(英文)
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.