Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts

The paper introduces decision checkpoints that log observations and tool actions during inference, enabling the assignment of outcome categories to scientific-search agent responses. Using these checkpoints on 540 AutoResearchBench questions, the authors compare keyword search and read-first strategies, finding that keyword search yields 24.6% accuracy while raw search achieves 17.8%. The checkpoint protocol reveals detailed differences in target exposure, inspection attempts, and evidence-search calls that aggregate accuracy alone obscures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• benchmarks