arXiv cs.CL
· Papers
Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards
arXiv:2608.07531v1 Announce Type: new Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing external rewards provide either sparse outcome supervision or richer feedback from process annotations and LLM judges. Outcom