Proper Scoring Rules for Agentic Uncertainty Quantification 事件

Proper Scoring Rules for Agentic Uncertainty Quantification arXiv:2605.24756v1 Announce Type: new Abstract: Language-model agents increasingly emit uncertainty signals throughout a trajectory, but existing agentic UQ evaluations often conflate ranking usefulness with probabilistic truthfulness. AUROC, AUPRC, risk-coverage, Trajectory ECE, and scalarized trajectory scores evaluate discrimination, binwise calibration, or collapsed summaries, but do not strictly elicit the full prefix-conditioned