Story
arxiv_cs_ai · Jul 31, 2026 · paper
Source brief
Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember
arxiv.orgJul 31, 2026
original source linked
In brief
Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly shape future practice. External skil...
Feed lens
agentevaluation