TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization

摘要

Reinforcement Learning (RL) with sparse outcome rewards suffers from inefficient credit assignment in complex LLM reasoning tasks. While utilizing stronger LLMs as teachers to derive dense token-level supervision offers a cost-effective alternative to proprietary reward models, it relies on the flawed assumption that teachers are perfect oracles. In reality, teacher models exhibit capability limitations and uncertainty, producing noisy signals that make student policies susceptible to reward hacking. To address this, we propose Teacher Reward Adaptive Calibration (TRAC), a robust framework that filters noisy supervision by dynamically modulating teacher influence via a multi-granularity calibration mechanism. TRAC evaluates teacher reliability across three principled dimensions: problem-level expertise, trajectory-level discrimination, and token-level confidence. Furthermore, we integrate TRAC with Group Relative Policy Optimization (GRPO), formulating as TRAC-GRPO, which treats calibrated teacher-derived reward as an additive advantage reshaping term to ensure fair advantage estimation. Extensive experiments demonstrate that TRAC effectively mitigates teacher noise, significantly enhancing the reasoning capabilities and training stability of LLMs compared to standard baselines. The code will be available at: https://github.com/JIA-Lab-research/TRAC.