Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards

Excerpt

arXiv:2608.07531v2 Announce Type: replace 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. Outcome rewards scale readily but cannot distinguish grounded retrieval from redundant search, whereas richer signals require costly annotation or inference during training. Internal