Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Towards Robust Process Reward Modeling via Noise-aware Learning
Bin Xie, Bingbing Xu, Xueyun Tian +2
Process Reward Models (PRMs) have achieved strong results in complex reasoning, but are bottlenecked by costly process-level supervision. A widely used alternative, Monte Carlo Est…
cs.LG2026
RPO: Decoupling Rollout and Inference Policies for LLM Reasoning
Jingchu Wang, Bingbing Xu, Yige Yuan +4
Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference respon…