الباحثون

Ruochen Zhao

المنشورات 2

نسخة أولية وصول مفتوح

Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems

Zhe Yu, Zixuan Wang, Peidong Wang وآخرون · 2026

Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves establish whether it is sufficient to judge task duties. We define execution consisten …

نسخة أولية وصول مفتوح

Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models

Yadong Xi, Rongsheng Zhang, Tangjie Lv وآخرون · 2026

Reinforcement learning with binary correctness rewards trains correctness, not calibrated confidence. The confidence that reasoning models verbalize is systematically overconfident, and the problem is not merely one of scale: verbalized confidence tracks how willing a model is to commit to an answer, not how likely the …

المؤلفون المشاركون