大模型推理能力 - arXivDaily 专题

2509.06945 2025-09-10 cs.CV cs.AI cs.CL cs.LG 82%

Interleaving Reasoning for Better Text-to-Image Generation

Wenxuan Huang, Shuang Chen, Zheyong Xie, Shaosheng Cao, Shixiang Tang, Yufan Shen, Qingyu Yin, Wenbo Hu, Xiaoman Wang, Yuntian Tang, Junbo Qiao, Yue Guo, Yao Hu, Zhenfei Yin, Philip Torr, Yu Cheng, Wanli Ouyang, Shaohui Lin

机构 * East China Normal University（华东师范大学）； The Chinese University of Hong Kong（香港中文大学）； Xiaohongshu Inc.（小红书公司）； University of California, Los Angeles（加州大学洛杉矶分校）； Zhejiang University（浙江大学）； University of Oxford（牛津大学）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2508.15796 2025-08-25 cs.CL cs.AI cs.CY cs.LG 82%

Benchmarking the Legal Reasoning of LLMs in Arabic Islamic Inheritance Cases

Nouar AlDahoul, Yasir Zaki

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 5 pages, 3 figures

2508.15388 2025-08-22 cs.IR 82%

TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation

Yu Xia, Rui Zhong, Zeyu Song, Wei Yang, Junchen Wan, Qingpeng Cai, Chi Lu, Peng Jiang

专题命中复杂问题求解：chain-of-thought(title)；reasoning(abstract)；CoT(abstract)

2507.20766 2025-08-08 cs.CV 82%

Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

Yang Chen, Yufan Shen, Wenxuan Huang, Sheng Zhou, Qunshu Lin, Xinyu Cai, Zhi Yu, Jiajun Bu, Botian Shi, Yu Qiao

专题命中复杂问题求解：reasoning(title,abstract)；self-correction(abstract)

2508.03178 2025-08-06 cs.CL cs.AI cs.LG 82%

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

Chenyang Wang, Liang Wen, Shousheng Jia, Xiangzheng Zhang, Liang Xu

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 12 pages, 10 figures, 7 tables

2507.06183 2025-07-09 cs.CV 82%

Enhancing Scientific Visual Question Answering through Multimodal Reasoning and Ensemble Modeling

Prahitha Movva, Naga Harshita Marupaka

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）； University of Southern California（南加州大学）

专题命中复杂问题求解：reasoning(title,abstract)；chain-of-thought(abstract)

2506.18237 2025-06-24 cs.LG cs.AI cs.CL 82%

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Xu Wan, Wei Wang, Wenyue Xu, Wotao Yin, Jie Song, Mingyang Sun

机构 * Zhejiang University（浙江大学）； Alibaba DAMO Academy（阿里巴巴 DAMO 院）； Tongji University（同济大学）； Peking University（北京大学）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2506.08379 2025-06-11 cs.LG cs.AI cs.CL 82%

Reinforce LLM Reasoning through Multi-Agent Reflection

Yurun Yuan, Tengyang Xie

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments International Conference on Machine Learning (ICML), 2025

2503.04556 2025-06-11 cs.CL cs.AI cs.LG 82%

Compositional Causal Reasoning Evaluation in Language Models

Jacqueline R. M. A. Maasch, Alihan Hüyük, Xinnuo Xu, Aditya V. Nori, Javier Gonzalez

机构 * Harvard University（哈佛大学）； Microsoft Research Cambridge（微软研究院剑桥）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Journal ref The 42nd International Conference on Machine Learning (ICML 2025)

2506.04088 2025-06-05 cs.LG cs.AI cs.CL cs.CV 82%

Multimodal Tabular Reasoning with Privileged Structured Information

Jun-Peng Jiang, Yu Xia, Hai-Long Sun, Shiyin Lu, Qing-Guo Chen, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye

机构 * School of Artificial Intelligence, Nanjing University, China（人工智能学院，南京大学）； National Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学）； AI Business, Alibaba Group（阿里集团人工智能业务）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2506.02658 2025-06-05 cs.SE 82%

Computational Thinking Reasoning in Large Language Models

Kechi Zhang, Ge Li, Jia Li, Huangzhao Zhang, Jingjing Xu, Hao Zhu, Lecheng Wang, Jia Li, Yihong Dong, Jing Mai, Bin Gu, Zhi Jin

专题命中复杂问题求解：reasoning(title,abstract)；planning(abstract)

2506.02208 2025-06-04 cs.LG cs.AI cs.CL 82%

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning

Hongling Xu, Qi Zhu, Heyuan Deng, Jinpeng Li, Lu Hou, Yasheng Wang, Lifeng Shang, Ruifeng Xu, Fei Mi

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））； Huawei Noah’s Ark Lab（华为诺亚实验室）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2504.05258 2025-06-02 cs.LG cs.AI cs.CL 82%

Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models

Adrián Bazaga, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert

机构 * University of Cambridge（剑桥大学）； Amazon AGI（亚马逊人工智能研究院）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2025 (Main)

2505.22425 2025-05-29 cs.LG cs.AI cs.CL 82%

Scaling Reasoning without Attention

Xueliang Zhao, Wei Wu, Lingpeng Kong

机构 * The University of Hong Kong（香港大学）； Ant Group（蚂蚁集团）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments preprint

2505.21374 2025-05-28 cs.CV 82%

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

Junhao Cheng, Yuying Ge, Teng Wang, Yixiao Ge, Jing Liao, Ying Shan

机构 * ARC Lab, Tencent PCG（腾讯PCG广告实验室）； City University of Hong Kong（香港城市大学）

专题命中复杂问题求解：reasoning(title,abstract)；CoT(abstract)

Comments Homepage: https://github.com/TencentARC/Video-Holmes

2505.16886 2025-05-23 cs.IR cs.AI cs.CL cs.LG 82%

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?

Nour Jedidi, Yung-Sung Chuang, James Glass, Jimmy Lin

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2503.24370 2025-05-22 cs.LG cs.AI cs.CL 82%

Effectively Controlling Reasoning Models through Thinking Intervention

Tong Wu, Chong Xiang, Jiachen T. Wang, G. Edward Suh, Prateek Mittal

机构 * Princeton University（普林斯顿大学）； NVIDIA（英伟达）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2502.12202 2025-05-20 cs.CL cs.AI cs.LG 82%

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

Zihao Zhu, Hongbao Zhang, Ruotong Wang, Ke Xu, Siwei Lyu, Baoyuan Wu

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 39 pages, 13 tables, 14 figures

2504.04736 2025-04-29 cs.AI cs.CL cs.LG 82%

Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use

Anna Goldie, Azalia Mirhoseini, Hao Zhou, Irene Cai, Christopher D. Manning

机构 * Department of Computer Science Stanford University（计算机科学系斯坦福大学）

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2504.12951 2025-04-18 cs.CL cs.AI cs.LG 82%

Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback

Nearchos Potamitis, Akhil Arora

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 8 pages, 16 figures, 1 table. arXiv admin note: text overlap with arXiv:2405.06691

2411.03321 2025-04-07 cs.AI cs.CL cs.LG 82%

Towards More Accurate US Presidential Election via Multi-step Reasoning with Large Language Models

Chenxiao Yu, Zhaotian Weng, Yuangang Li, Zheng Li, Xiyang Hu, Yue Zhao

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This research is ongoing work. Xiyang Hu and Yue Zhao are the corresponding authors

2503.24388 2025-04-02 cs.AI cs.CL cs.CV cs.LG 82%

RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy

Zhonghan Zhao, Wenwei Zhang, Haian Huang, Kuikun Liu, Jianfei Gao, Gaoang Wang, Kai Chen

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2503.22200 2025-03-31 cs.SD cs.CV eess.AS 82%

Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization

Haomin Zhang, Sizhe Shan, Haoyu Wang, Zihao Chen, Xiulong Liu, Chaofan Ding, Xinhan Di

专题命中复杂问题求解：CoT(title,abstract)；chain-of-thought(abstract)

Comments 10 pages, 4 figures

2502.13942 2025-02-20 cs.CV 82%

A Chain-of-Thought Subspace Meta-Learning for Few-shot Image Captioning with Large Vision and Language Models

Hao Huang, Shuaihang Yuan, Yu Hao, Congcong Wen, Yi Fang

专题命中复杂问题求解：chain-of-thought(title,abstract)；CoT(abstract)

Comments 11 pages, 3 figures, 5 tables

2502.06807 2025-02-20 cs.LG cs.AI cs.CL 82%

Competitive Programming with Large Reasoning Models

OpenAI, :, Ahmed El-Kishky, Alexander Wei, Andre Saraiva, Borys Minaiev, Daniel Selsam, David Dohan, Francis Song, Hunter Lightman, Ignasi Clavera, Jakub Pachocki, Jerry Tworek, Lorenz Kuhn, Lukasz Kaiser, Mark Chen, Max Schwarzer, Mostafa Rohaninejad, Nat McAleese, o3 contributors, Oleg Mürk, Rhythm Garg, Rui Shu, Szymon Sidor, Vineet Kosaraju, Wenda Zhou

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2502.13025 2025-02-19 cs.AI cond-mat.mtrl-sci cs.CL cs.LG 82%

Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks

Markus J. Buehler

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2410.09302 2025-02-12 cs.LG cs.AI cs.CL 82%

Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization

Kaixuan Ji, Guanlin Liu, Ning Dai, Qingping Yang, Renjie Zheng, Zheng Wu, Chen Dun, Quanquan Gu, Lin Yan

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2501.14300 2025-01-27 cs.AI cs.CL cs.LG cs.SI 82%

Fast Think-on-Graph: Wider, Deeper and Faster Reasoning of Large Language Model on Knowledge Graph

Xujian Liang, Zhaoquan Gu

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2501.02026 2025-01-07 cs.CL cs.AI cs.LG cs.LO 82%

Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models

Kaleem Ullah Qasim, Jiashu Zhang, Tariq Alsahfi, Ateeq Ur Rehman Butt

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2412.16145 2024-12-30 cs.LG cs.AI cs.CL 82%

Offline Reinforcement Learning for LLM Multi-Step Reasoning

Huaijie Wang, Shibo Hao, Hanze Dong, Shenao Zhang, Yilin Bao, Ziran Yang, Yi Wu

专题命中复杂问题求解：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

1. 复杂问题求解 4991 篇

Interleaving Reasoning for Better Text-to-Image Generation

Benchmarking the Legal Reasoning of LLMs in Arabic Islamic Inheritance Cases

TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation

Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following

Enhancing Scientific Visual Question Answering through Multimodal Reasoning and Ensemble Modeling

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Reinforce LLM Reasoning through Multi-Agent Reflection

Compositional Causal Reasoning Evaluation in Language Models

Multimodal Tabular Reasoning with Privileged Structured Information

Computational Thinking Reasoning in Large Language Models

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning

Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models

Scaling Reasoning without Attention

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?

Effectively Controlling Reasoning Models through Thinking Intervention

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use

Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback

Towards More Accurate US Presidential Election via Multi-step Reasoning with Large Language Models

RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy

Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization

A Chain-of-Thought Subspace Meta-Learning for Few-shot Image Captioning with Large Vision and Language Models

Competitive Programming with Large Reasoning Models

Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks

Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization

Fast Think-on-Graph: Wider, Deeper and Faster Reasoning of Large Language Model on Knowledge Graph

Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models

Offline Reinforcement Learning for LLM Multi-Step Reasoning