Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents
Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising approach for post-training such agents, but its reliance on sparse, outcome-based supervision can make credit assignment...
Wenyu Huang, Xin-Yu Hou, P. Vougiouklis et al.
· 0 citations