Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents? 事件

Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents? arXiv:2605.27881v1 Announce Type: new Abstract: Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison: existing works differ in retrieval corpora, reward designs, and training protocols, making it unclear what actually drives impro