$\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data 事件

$\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data arXiv:2604.14054v2 Announce Type: replace-cross Abstract: Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit assignment, and limited labeled data. Self-play offers a scalable route to reduce data dependence, but conventional self-play optimizes students only through sparse outcome