Agentic Transformers Provably Learn to Search via Reinforcement Learning 事件

Agentic Transformers Provably Learn to Search via Reinforcement Learning arXiv:2606.00183v1 Announce Type: cross Abstract: Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives. Yet, we lack a theoretical understanding of how transformer-based policies acquire such search capabilities from the training dynamics of reinforcement learning (RL). We study this q