arXiv AI

TIDE: Token-Level Credit Assignment via Entropy-Gated Bounded Deviation

TIDE (Token-level Importance via Deviation and Entropy) is a critic‑free reinforcement learning framework that replaces the volatile reverse KL divergence with a bounded Hellinger distance to safely quantify token‑level exploration. It introduces an entropy gating mechanism that scales deviation by policy uncertainty, redistributing sequence‑level advantage across tokens and amplifying exploratory steps while suppressing low‑entropy deviations. Experiments on the Qwen2.5‑32B backbone show TIDE achieving 60.0% and 46.0% Avg@32 accuracy on AIME 2024 and AIME 2025, outperforming strong critic‑free baselines such as DAPO.

arXiv AI
Jun 19

Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning

arXiv:2606. 19771v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instability: uniform token updates precipitate entropy collapse, leading to premature convergence to suboptimal strategies, whereas excessive Shannon Entropy maximization can cause entropy explosion, driving blind exploration toward incoherent reasoning chains.

By Xuanzhi Feng, Zhengyang Li, Zeyu Liu, Haoxi Li, Yuming Jiang, Bing Guo, Jingcai Guo, Jie Zhang, Song Guo
arXiv AI
Jun 18

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

arXiv:2606. 19236v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training.

By Haipeng Luo, Qingfeng Sun, Songli Wu, Can Xu, Wenfeng Deng, Han Hu, Yansong Tang
arXiv AI
Oct 31

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

AEM: Adaptive Entropy Modulation for Multi‑Turn Agentic Reinforcement Learning proposes a supervision‑free credit assignment technique that adjusts entropy dynamics at the response level during RL training. By aligning uncertainty estimation with the granularity of LLM agent actions and rescaling advantages based on a response‑level uncertainty proxy, AEM improves the exploration‑exploitation balance without relying on dense intermediate supervision. Experiments on ALFWorld, WebShop, and SWE‑bench‑Verified show consistent performance gains across models from 1.5B to 32B, including a 1.4% improvement in a state‑of‑the‑art software‑engineering RL framework.

By Haotian Zhao, Songlin Zhou, Yuxin Zhang, Stephen S. -T. Yau, Wenyu Zhang, Lun Tian, Tianshu Zhu, Yifeng Huang, Yucheng Zeng, Jingnan Gu, Daxiang Dong, Jianmin Wu
arXiv AI
Jun 24

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

arXiv:2606. 24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason.

By Tianyuan Shi, Canbin Huang, Bei Li, Xin Chen, Xiaojun Quan, Jingang Wang, Qifan Wang
arXiv AI
Aug 26

Contrastive Branch Policy Optimization

Contrastive Branch Policy Optimization (CBPO) is a reinforcement learning method that separates the allocation of a fixed rollout budget from the translation of branch outcomes into token-level credit. It uses generation entropy to screen branch positions, path- and node-level decay to distribute the budget, and Contrastive Branch Value (CBV) to estimate local decision sensitivity without changing reward signs. CBPO partitions trajectories into non-overlapping credit segments, preventing duplicated gradients and enabling fine-grained credit assignment using only outcome rewards.

By Ying Wang, Changlin Qiu, Bang Lin, Linbo Jin, Wen Jiang, Zhe Sun, Jingli Yang
arXiv AI
Sep 25

DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs

The paper introduces DEEPO, a Dual-Entropy Enhanced Policy Optimization method designed to mitigate hallucination in multimodal large language models (MLLMs). It addresses two weaknesses in reinforcement learning: (1) hard queries with high semantic entropy produce uniformly wrong samples, erasing advantage signals, and (2) confident-but-wrong tokens become invisible to gradients as the policy sharpens. DEEPO combines semantic‑entropy‑triggered expert prefixes to inject grounded continuations and Renyi preconditioning to counter logit saturation, yielding significant hallucination reduction while maintaining accuracy and training stability.

By Yingxuan Zhuang, Miao Pan, Wangjie Gan, Jingxiao Yang, Fan Wang, Weiming Liu, Cheng Tan, Xuhong Zhang, Jintao Chen