SOURCE-LINKED INTELLIGENCE

DualStake: Dual-Path Confidence Calibration in Deep Research Agents

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. However, these agents suffer from severe overconfidence, making their expressed confidence unreliable for user trust and downstream abstention. To address this, we augment the Deep Research pipeline with step confidence elicitation after each retrieval, building on the commonly used post-answer verbalized confidence. Interestingly, we find that Evidence Confidence (E-Conf), elicited after the final retrieval step, provides a stronger uncertainty signal than Answer Confidence (A

Read original source ↗ Open in workspace

recordType

paper

region

Global