English
Related papers

Related papers: Step Potential Advantage Estimation: Harnessing In…

200 papers

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Machine Learning · Computer Science 2025-07-31 Zijing Zhang , Ziyang Chen , Mingxiao Li , Zhaopeng Tu , Xiaolong Li

Mathematical reasoning through Chain-of-Thought (CoT) has emerged as a powerful capability of Large Language Models (LLMs), which can be further enhanced through Test-Time Scaling (TTS) methods like Beam Search and DVTS. However, these…

Computation and Language · Computer Science 2025-05-26 Zezhong Wang , Xingshan Zeng , Weiwen Liu , Yufei Wang , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu , Kam-Fai Wong

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…

Artificial Intelligence · Computer Science 2025-10-30 Tianqianjin Lin , Xi Zhao , Xingyao Zhang , Rujiao Long , Yi Xu , Zhuoren Jiang , Wenbo Su , Bo Zheng

Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce…

Machine Learning · Computer Science 2026-05-25 Xin-Qiang Cai , Wei Wang , Feng Liu , Tongliang Liu , Gang Niu , Masashi Sugiyama

While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the consistency between the final result and the ground truth,…

Computation and Language · Computer Science 2026-02-13 Xiangfeng Wang , Hangyu Guo , Yanlin Lai , Mitt Huang , Liang Zhao , Chengyuan Yao , Yinmin Zhang , Qi Han , Xiaoxiao Ren , Chun Yuan , Tong Xu , Zheng Ge , Xiangyu Zhang , Daxin Jiang

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a…

Computation and Language · Computer Science 2026-05-12 Zichao Yu , Shengze Xu , Bingqing Jiang , Wenyi Zhang , Difan Zou

Reinforcement Learning with Verifiable Rewards (RLVR) has become a central approach for improving the reasoning ability of large language models. Recent work studies RLVR through token entropy, arguing that high-entropy tokens drive…

Machine Learning · Computer Science 2025-12-02 Xinzhu Chen , Xuesheng Li , Zhongxiang Sun , Weijie Yu

Although LLMs exhibit strong reasoning capabilities, existing training methods largely depend on outcome-based feedback, which can produce correct answers with flawed reasoning. Prior work introduces supervision on intermediate steps but…

Computation and Language · Computer Science 2026-01-30 Jundong Xu , Hao Fei , Huichi Zhou , Xin Quan , Qijun Huang , Shengqiong Wu , William Yang Wang , Mong-Li Lee , Wynne Hsu

Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labels for reward…

Machine Learning · Computer Science 2026-05-26 Li Wang , Xiaodong Lu , Xiaohan Wang , Yikun Ban , Jiajun Chai , Wei Lin , Tianhao Peng , Guojun Yin

Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape…

Artificial Intelligence · Computer Science 2026-05-28 Kohsei Matsutani , Shota Takashiro , Gouki Minegishi , Takeshi Kojima , Yusuke Iwasawa , Yutaka Matsuo

Reinforcement learning algorithms often suffer from slow convergence due to sparse reward signals, particularly in complex environments where feedback is delayed or infrequent. This paper introduces the Psychological Regret Model (PRM), a…

Machine Learning · Computer Science 2026-02-04 Zhe Xu

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Yingqian Min , Kun Zhou , Yifan Li , Yuhuan Wu , Han Peng , Yifan Du , Wayne Xin Zhao , Min Yang , Ji-Rong Wen

Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore treat imperfect step-level reward predictions as reliable…

Computation and Language · Computer Science 2026-05-18 Jinyuan Li , Langlin Huang , Chengsong Huang , Shaoyang Xu , Donghong Cai , Yuyi Yang , Wenxuan Zhang , Jiaxin Huang

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

Reinforcement Learning with Verifiable Rewards (RLVR) has been an effective approach for improving Large Language Models' reasoning in domains such as coding and mathematics. Here, we apply RLVR methods towards forecasting future real-world…

Machine Learning · Computer Science 2025-12-02 Benjamin Turtel , Danny Franklin , Kris Skotheim , Luke Hewitt , Philipp Schoenegger

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the…

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a…

Machine Learning · Computer Science 2026-04-28 Shipeng Li , Zhiqin Yang , Shikun Li , Xiaobo Xia , Hengyu Liu , Xinghua Zhang , Gaode Chen , Dong Fang , Ying Tai , Zhe Peng

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Jiahao Wang , Weiye Xu , Aijun Yang , Wengang Zhou , Lewei Lu , Houqiang Li , Xiaohua Wang , Jinguo Zhu

Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs), but often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers during…

Computation and Language · Computer Science 2025-08-19 Yuanfeng Xu , Zehui Dai , Jian Liang , Jiapeng Guan , Guangrun Wang , Liang Lin , Xiaohui Lv

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks…

Artificial Intelligence · Computer Science 2025-09-09 Haoyang He , Zihua Rong , Kun Ji , Chenyang Li , Qing Huang , Chong Xia , Lan Yang , Honggang Zhang