English
Related papers

Related papers: SSPO: Self-traced Step-wise Preference Optimizatio…

200 papers

As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (CoT) generation length, thereby enhancing reasoning…

Artificial Intelligence · Computer Science 2025-05-20 Muzhi Dai , Chenxu Yang , Qingyi Si

Large reasoning models trained with reinforcement learning and verifiable rewards (RLVR) achieve strong performance on complex reasoning tasks, yet often overthink, generating redundant reasoning without performance gains. Existing…

Computation and Language · Computer Science 2026-04-20 Shuaiyi Nie , Siyu Ding , Wenyuan Zhang , Linhao Yu , Tianmeng Yang , Yao Chen , Weichong Yin , Yu Sun , Hua Wu , Tingwen Liu

Medical question answering requires advanced reasoning that integrates domain knowledge with logical inference. However, existing large language models (LLMs) often generate reasoning chains that lack factual accuracy and clinical…

Computation and Language · Computer Science 2025-12-09 Chia-Hsuan Hsu , Jun-En Ding , Hsin-Ling Hsu , Chih-Ho Hsu , Li-Hung Yao , Chun-Chieh Liao , Feng Liu , Fang-Ming Hung

Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital…

Robotics · Computer Science 2025-12-02 Senyu Fei , Siyin Wang , Li Ji , Ao Li , Shiduo Zhang , Liming Liu , Jinlong Hou , Jingjing Gong , Xianzhong Zhao , Xipeng Qiu

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

Artificial Intelligence · Computer Science 2026-05-29 Zhe Qian , Nianbing Su , Zhonghua Wang , Hebei Li , Zhongxing Xu , Yueying Li , Fei Luo , Zhuohan Ouyang , Yanbiao Ma

Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all tokens in a trajectory. Such uniform assignment ignores which…

Artificial Intelligence · Computer Science 2026-05-27 Ankur Samanta , Akshayaa Magesh , Ayush Jain , Youliang Yu , Daniel Jiang , Kavosh Asadi , Kaveh Hassani , Paul Sajda , Jalaj Bhandari , Yonathan Efroni

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning.…

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance,…

Computation and Language · Computer Science 2025-03-06 Shimao Zhang , Xiao Liu , Xin Zhang , Junxiao Liu , Zheheng Luo , Shujian Huang , Yeyun Gong

Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy…

Artificial Intelligence · Computer Science 2025-08-15 Xingyu Wu , Yuchen Yan , Shangke Lyu , Linjuan Wu , Yiwen Qiu , Yongliang Shen , Weiming Lu , Jian Shao , Jun Xiao , Yueting Zhuang

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Computation and Language · Computer Science 2025-04-15 Yutao Mou , Yuxiao Luo , Shikun Zhang , Wei Ye

Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This…

Machine Learning · Computer Science 2025-08-11 Si Shen , Peijun Shen , Wenhua Zhao , Danhao Zhu

Prompt optimization is a practical and widely applicable alternative to fine tuning for improving large language model performance. Yet many existing methods evaluate candidate prompts by sampling full outputs, often coupled with self…

Computation and Language · Computer Science 2025-09-19 Chenzhuo Zhao , Ziqian Liu , Xinda Wang , Junting Lu , Chaoyi Ruan

A major drawback of reasoning models is their excessive token usage, inflating computational cost, resource demand, and latency. We show this verbosity stems not from deeper reasoning but from reinforcement learning loss minimization when…

Computation and Language · Computer Science 2025-11-24 Mehdi Fatemi , Banafsheh Rafiee , Mingjie Tang , Kartik Talamadupula

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…

Machine Learning · Computer Science 2026-02-04 Ruiyi Ding , Yongxuan Lv , Xianhui Meng , Jiahe Song , Chao Wang , Chen Jiang , Yuan Cheng

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of reasoning tasks. Recent methods have further improved LLM performance in complex mathematical reasoning. However, when extending these methods…

Artificial Intelligence · Computer Science 2025-11-11 Chen He , Xun Jiang , Lei Wang , Hao Yang , Chong Peng , Peng Yan , Fumin Shen , Xing Xu

Large Reasoning Models (LRMs) achieve explicit chain-of-thought expansion by imitating deep thinking behaviors of humans, demonstrating excellent performance in complex task scenarios. However, the deep-thinking mode often leads to…

Machine Learning · Computer Science 2026-01-30 Qian Wan , Ziao Xu , Luona Wei , Xiaoxuan Shen , Jianwen Sun

The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However, research indicates that these paths are not always…

Computation and Language · Computer Science 2024-11-01 Xuan Zhang , Chao Du , Tianyu Pang , Qian Liu , Wei Gao , Min Lin

Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs have been proposed to improve the \textit{reasoning} or \textit{thinking} capabilities of LLMs…

Artificial Intelligence · Computer Science 2025-10-22 Jiahao Yu , Zelei Cheng , Xian Wu , Xinyu Xing

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Computation and Language · Computer Science 2025-11-03 Fenia Christopoulou , Ronald Cardenas , Gerasimos Lampouras , Haitham Bou-Ammar , Jun Wang

Chain-of-thought (CoT) improves reasoning reliability but increases token cost, motivating post-training compression of explicit reasoning traces. However, the shortest sufficient reasoning is not universal: it depends on difficulty, model…

Artificial Intelligence · Computer Science 2026-03-10 Ye Tian , Aijun Liu
‹ Prev 1 4 5 6 7 8 10 Next ›