AI RESEARCH
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
arXiv CS.CL
•
ArXi:2605.04018v1 Announce Type: new Reasoning-intensive retrieval aims to surface evidence that s downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide complementary evidence across iterative search and synthesis. However, existing work remains limited on both evaluation and