Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
Jiaxin Zhang, Xiangyu Peng, Qinglin Chen +3
Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental consequences, leaving the agen…
cs.LG2026
The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation
Jiaxin Zhang, Xiangyu Peng, Qinglin Chen +3
On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effe…