Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood

arXiv:2604.12736v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly in their mathemat ical reasoning performance. However, GRPO and related entropy regularization methods still struggle with token-level sparse-rewards, which is an inherent chal lenge in chain-of-thought (CoT) reasoning. These approaches often rely on undifferen tiated token-level entropy regularization, which easily leads to entropy collapse or model degradation under sparse token rewards. In this work, we propose TEPO, a novel token-level framework that (1) leverages sequence-level likelihood to link group-level rewards with individual tokens via token-level aggregation, and (2) introduces a token-level KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates. Experiments demonstrate that TEPO not only achieves state-of-the-art performance on mathematical reasoning benchmarks but also markedly enhances training stability, reducing convergence time by 50% compared with GRPO/DAPO.

Related

• SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
• Rethinking Token-Level Credit Assignment in RLVR: A Polarity-Entropy Analysis
• SSPO: Subsentence-level Policy Optimization
• Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
• Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation

Source: arXiv cs.CL | 2026-04-15