4 papers · 1 filter
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…
Speculate with Memory: Lossless Acceleration for LLM Agents
Yu Li, Qinyuan Ye, Prafulla Kumar Choubey +2
Speculative execution accelerates LLM agents by using a smaller, cheaper model to predict and pre-launch the next step while the environment is idle. However, existing speculators…
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…
Nudging the Boundaries of LLM Reasoning
Justin Chih-Yao Chen, Becky Xiangyu Peng, Prafulla Kumar Choubey +4
Current online reinforcement learning (RL) algorithms like GRPO share a key limitation in LLM reasoning: they cannot learn from problems that are "unsolvable" to the model. In othe…