paper-with-me

Papers

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

2026-04-14 · Xingyu Lin, Yilin Wen, Du Su, Jinchang Hou, En Wang, Wenbin Liu, Chenfu Bao, Zhonghou Lv arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.12736

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Similar Papers 제목 키워드 기반

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

2025-10-10 · Xingyu Lin, Yilin Wen, En Wang, Du Su 외 arxiv

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regul…

Mathematical Reasoning

Orchestrating Tokens and Sequences: Dynamic Hybrid Policy Optimization for RLVR

2026-01-09 · Zijun Min, Bingshuai Liu, Ante Wang, Long Zhang 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising framework for optimizing large language models in reasoning tasks. However, existing RLVR algorithms focus on different granularities, and each has…

Reinforcement LearningMathematical Reasoning

GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control

2025-08-05 · Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino 외 arxiv

Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, w…

SSPO: Subsentence-level Policy Optimization

2025-11-06 · Kun Yang, Zikang chen, Yanmeng Wang, Zhigen Li 외 arxiv

As a key component of large language model (LLM) post-training, Reinforcement Learning from Verifiable Rewards (RLVR) has substantially improved reasoning performance. However, existing RLVR algorithms exhibit distinct s…

Reinforcement Learning

Geometric-Mean Policy Optimization

2025-07-28 · Yuzhong Zhao, Yue Liu, Junpeng Liu, Jingye Chen 외 arxiv

Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unfortunately, GRPO is observed to suffer f…

Mathematical Reasoning