Does Recursive Knowledge Construction Help Agents Verify Consensus Claims in Science?

arXiv cs.AINovember 2, 2026en

arXiv:2610.40906v1 Announce Type: new Abstract: Recent scientific agents build knowledge recursively by retrieving evidence, constructing an intermediate state, and judging whether that state contains sufficient information. These agents are evaluated end-to-end, usually without ground truth, so the effect of each design choice is unknown. Here, we examined two design axes: (1) what the recursion builds (the state of evidence) and (2) what controls it (the judge that decides when to stop). To measure them, we defined consensus scientific claim verification and measured these effects on this task, where a system must establish a claim's consensus stance from the open literature. We built a ne

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Agenter