Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR
Kun Liang, Chenming Tang, Clive Bai +5
Assigning credit to intermediate steps remains a central challenge in training Large Language Models (LLMs) on multi-step reasoning tasks with sparse terminal rewards, and actor-cr…
cs.LG2026
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
Kun Liang, Chenming Tang, Clive Bai +3
On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties ev…
cs.LG2026
ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
Kun Liang, Clive Bai, Xin Xu +5
Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thought (CoT) reasoning, but uniformly applying overlong reasoning at inference tim…