HISPO introduces a segment‑level policy‑optimization technique for reinforcement learning with verifiable rewards, creating entropy‑derived contiguous segments during rollout and applying clipped importance‑sampling correction at this granularity. It bridges the gap between token‑level and sequence‑level corrections, offering a middle‑ground approach for credit assignment in long‑form mathematical reasoning. Evaluated on Qwen3‑1.7B‑Base across six benchmarks, HISPO consistently outperforms or matches the strongest baselines in Pass@8 and Acc@8 metrics, notably improving AIME25 scores over GRPO and GSPO.
By Quoc-Vinh Lai-Dang, Hyo-Sang Shin
The paper introduces Selective Successor Eligibility Traces (S-trace), a critic‑free eligibility trace method designed to improve temporal credit assignment in Reinforcement Learning with Verifiable Rewards (RLVR). S-trace reweights successor importance to recover downstream credit signals under PPO-style clipping and selectively propagates them to historical tokens using entropy-based token selection. Experiments on Qwen3 models show that S-trace yields significant absolute gains in average pass@16 over GRPO and trace-style GRPO, while also producing shorter responses.
By Chaoli Mou, Xinning Chen, Zhan Zhuang, Qinghe Zheng, Deyuan Kong, Yu Zhang
arXiv:2606. 08543v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning but often suffers from rapid policy-entropy collapse, where the policy prematurely concentrates on narrow high-probability reasoning paths.
By Shumeng Yang, Yisu Liu, Jiayi Zheng, Zhaohui Yang, Linjing Li
arXiv:2606. 31575v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a powerful tool for propelling Large Language Models (LLMs) beyond imitation-based training towards more robust reasoning capabilities.
By Outongyi Lv, Yanzhao Zheng, Yuanwei Zhang, Zhenghao Huang, Xingjun Wang, Baohua Dong, Hangcheng Zhu, Yingda Chen
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:2610.20497v1 Announce Type: new
Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models from checked task outcomes, but assigning a terminal reward to individual...
By Wei Chen, Yubing Wu, Zhou Xu, Haoyue Zhang, Delu Zeng, Jiahao Wang, Junmei Yang, Pan tiewen, Jingfeng Liu, Zhiheng Zhou, Bo Li, Min Chen
arXiv:2607. 03126v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has substantially improved the reasoning ability of large language models (LLMs), but sparse outcome rewards still make token-level credit assignment difficult.
By Zijun Xie, Yuyang You, Yongzhi Li, Enlei Gong, Zeyu Chen, Quan Chen, Yanhua Cheng, Peng Jiang, Yadong Mu
arXiv:2606. 16154v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but GRPO-style optimization remains prone to collapse.
By Prasanth YSS, Zhichen Ren, Rasa Hosseinzadeh, Ilan Gofman, Yuqi Chen, Zhaoyan Liu, Guangwei Yu, Jesse C. Cresswell, Satya Krishna Gorti
arXiv:2606. 18810v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps.
By Yingyu Shan, Yuhang Guo, Zihao Cheng, Zeming Liu, Xiangrong Zhu, Xinyi Wang, Jiashu Yao, Wei Lin, Hongru Wang, Heyan Huang
arXiv:2610.18704v1 Announce Type: new
Abstract: In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward mode...
By Sitong Wu, Haoru Tan, Bin Xia, Xichen Zhang, Jingyao Li, Shaofeng Zhang, Xiaojuan Qi, Bei Yu, Jiaya Jia
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps. Existing token-level credit assignment methods require resources beyond the model's own rollouts.
arXiv:2607. 03126v3 Announce Type: replace Abstract: Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their unequal contributions to the reasoning process.
By Zijun Xie, Yuyang You, Yongzhi Li, Enlei Gong, Quan Chen, Yanhua Cheng, Peng Jiang, Binbin Zheng, Xiaolong Liu, Zeyu Chen, Yadong Mu