Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses 事件

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses arXiv:2606.02373v1 Announce Type: cross Abstract: Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which constraints remain open, and which claims have actually been checked. We argue that this formulation puts too much routine state management inside the policy: reinforcement learning i