The Bidirectional Process Reward Model
By: Lingyin Zhang , Jun Gao , Xiaoxue Ren and more
Potential Business Impact:
Helps AI check its thinking both ways.
Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning quality of Large Language Models (LLMs) by assigning fine-grained scores to intermediate reasoning steps within a solution trajectory. However, existing PRMs predominantly adopt a unidirectional left-to-right (L2R) evaluation paradigm, which limits their ability to leverage global context, making it challenging to verify the consistency of earlier steps based on later ones. In light of these challenges, we propose a novel bidirectional evaluation paradigm, named Bidirectional Process Reward Model (BiPRM). BiPRM seamlessly incorporates a parallel right-to-left (R2L) evaluation stream alongside the conventional L2R flow, enabling later reasoning steps to help assess earlier ones in real time. Notably, the built-in R2L evaluation is implemented solely through prompt modifications that reverse the original reasoning trajectory, without any additional parameters or inference latency introduced. This ensures BiPRM remains both efficient and broadly compatible with existing PRM studies. We conduct extensive experiments on two mathematical reasoning benchmarks using samples generated by three different policy models. Our method, BiPRM, is evaluated across three backbones and three distinct PRM objectives. Across all settings, BiPRM consistently outperforms unidirectional baselines, achieving up to a 31.9% improvement in stepwise reward evaluation. Generally, our results highlight BiPRM's effectiveness, robustness, and general applicability, offering a promising new direction for process-based reward modeling.
Similar Papers
Better Process Supervision with Bi-directional Rewarding Signals
Computation and Language
Helps AI solve hard math problems better.
A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models
Computation and Language
Teaches computers to think step-by-step.
AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
Computation and Language
Helps AI make better choices step-by-step.