大模型推理能力

2510.19767 2025-10-23 cs.CL cs.AI cs.LG 85%

SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration

Xichen Zhang, Sitong Wu, Haoru Tan, Shaozuo Yu, Yinghao Zhu, Ziyi He, Jiaya Jia

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； The Chinese University of Hong Kong（香港中文大学）； The University of Hong Kong（香港大学）

专题命中数学推理：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Code: https://github.com/dvlab-research/SmartSwitch

2501.19339 2025-10-23 cs.CV cs.CL 70%

PixelWorld: How Far Are We from Perceiving Everything as Pixels?

Zhiheng Lyu, Xueguang Ma, Wenhu Chen

机构 * University of Waterloo（滑铁卢大学）； Vector Institute, Toronto（多伦多向量研究所）

专题命中数学推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

2510.19779 2025-10-23 cs.CL cs.AI cs.LG 67%

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

Yuezhou Hu, Jiaxin Guo, Xinyu Feng, Tuo Zhao

机构 * University of California, Berkeley（加州大学伯克利分校）； Tsinghua University（清华大学）； Georgia Institute of Technology（佐治亚理工学院）

专题命中数学推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2510.19506 2025-10-23 cs.CL 57%

Lookahead Routing for Large Language Models

Canbin Huang, Tianyuan Shi, Yuhua Zhu, Ruijun Chen, Xiaojun Quan

机构 * School of Computer Science and Engineering, Sun Yat-sen University, China（中山大学计算机科学与工程学院）； Shenzhen Loop Area Institute, China（深圳环湖研究所）

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2510.19176 2025-10-23 cs.AI cs.CL 88%

The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models

Yuqiao Tan, Shizhu He, Kang Liu, Jun Zhao

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院）； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

专题命中逻辑推理：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；logical reasoning(abstract)

Comments Accepted by NeurIPS'25 Efficient Reasoning Workshop

2510.19429 2025-10-23 cs.AI 79%

NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning

Wonje Choi, Jooyoung Kim, Honguk Woo

专题命中逻辑推理：reasoning(title,abstract)；分类 cs.AI

Comments Accepted at NeurIPS 2025

2510.19247 2025-10-23 cs.CL 79%

SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets

Ziwei Wang, Jiayuan Su, Mengyu Zhou, Huaxing Zeng, Mengni Jia, Xiao Lv, Haoyu Dong, Xiaojun Ma, Shi Han, Dongmei Zhang

专题命中逻辑推理：reasoning(title,abstract)；分类 cs.CL

2510.19493 2025-10-23 cs.CL 70%

What is the Best Sequence Length for BABYLM?

Suchir Salhan, Richard Diehl Martinez, Zébulon Goriely, Paula Buttery

机构 * Department of Computer Science & Technology, University of Cambridge, U.K.（计算机科学与技术系，剑桥大学，英国）； ALTA Institute, University of Cambridge, U.K.（ALTA研究所，剑桥大学，英国）

专题命中逻辑推理：reasoning(abstract)；logical reasoning(abstract)；分类 cs.CL

Comments Paper Accepted at the 2025 BabyLM Workshop @ EMNLP (Suzhou, China)

2510.19263 2025-10-23 cs.AI 57%

An Argumentative Explanation Framework for Generalized Reason Model with Inconsistent Precedents

Wachara Fungwacharakorn, Gauvain Bourgne, Ken Satoh

机构 * Center for Juris-Informatics, ROIS-DS, Tokyo, Japan（法律信息中心，ROIS-DS，东京，日本）； LIP6, Sorbonne University, CNRS, Paris, France（LIP6，索邦大学，CNRS，巴黎，法国）

专题命中逻辑推理：reasoning(abstract)；分类 cs.AI

Comments 10 pages, extended version for JURIX 2025 submission

2506.16962 2025-10-23 cs.CV cs.AI cs.CL 86%

Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search

Haoran Sun, Yankai Jiang, Wenjie Lou, Yujie Zhang, Wenjie Li, Lilong Wang, Mianxin Liu, Lei Liu, Xiaosong Wang

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Fudan University（复旦大学）； Shanghai Jiao Tong University（上海交通大学）

专题命中规划推理：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

2506.18167 2025-10-23 cs.LG cs.AI 82%

Understanding Reasoning in Thinking Language Models via Steering Vectors

Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda

机构 * University of Oxford（牛津大学）； University of Buenos Aires（布宜诺斯艾利斯大学）

专题命中规划推理：reasoning(title,abstract)；分类 cs.AI、cs.LG；planning(comments)

Comments Accepted to the Workshop on Reasoning and Planning for Large Language Models at ICLR 2025

2510.19048 2025-10-23 cs.CY cs.AI 79%

REPAIR Approach for Social-based City Reconstruction Planning in case of natural disasters

Ghulam Mudassir, Antinisca Di Marco, Giordano d'Aloisio

专题命中规划推理：planning(title,abstract)；分类 cs.AI

Comments Accepted at International Journal of Data Science and Analytics

2510.19213 2025-10-23 physics.med-ph 78%

AI in Proton Therapy Treatment Planning: A Review

Yuzhen Ding, Hongying Feng, Martin Bues, Mirek Fatyga, Tianming Liu, Thomas J. Whitaker, Haibo Lin, Nancy Y. Lee, Charles B. Simone, Samir H. Patel, Daniel J. Ma, Steven J. Frank, Sujay A. Vora, Jonathan A. Ashman, Wei Liu

专题命中规划推理：planning(title,abstract)

2510.19001 2025-10-23 cs.CV cs.AI cs.RO 77%

Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts

Seungjun Yu, Junsung Park, Youngsun Lim, Hyunjung Shim

专题命中规划推理：reasoning(abstract)；chain-of-thought(abstract)；planning(abstract)；分类 cs.AI

2510.19818 2025-10-23 cs.LG cs.AI cs.RO 62%

Semantic World Models

Jacob Berg, Chuning Zhu, Yanda Bao, Ishan Durugkar, Abhishek Gupta

机构 * University of Washington（华盛顿大学）； Sony AI（索尼人工智能）

专题命中规划推理：planning(abstract)；分类 cs.AI、cs.LG

2510.19631 2025-10-23 cs.AI cs.CL cs.MA 62%

HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application

Yiqian Yang, Tian Lan, Qianghuai Jia, Li Zhu, Hui Jiang, Hang Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang

机构 * Alibaba International Digital Commerce（阿里巴巴国际数字商业）

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI

2510.19245 2025-10-23 cs.CY cs.AI cs.HC cs.LG cs.MM 62%

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents

Yimeng Zhang, Jiri Gesi, Ran Xue, Tian Wang, Ziyi Wang, Yuxuan Lu, Sinong Zhan, Huimin Zeng, Qingjun Cui, Yufan Guo, Jing Huang, Mubarak Shah, Dakuo Wang

机构 * Michigan State University（密歇根州立大学）； Amazon（亚马逊）； Northeastern University（东北大学）； Northwestern University（西北大学）； University of Central Florida（佛罗里达中央大学）

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

2506.00711 2025-10-23 cs.LG cs.AI cs.CV 62%

QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training

Wei Dai, Peilin Chen, Chanakya Ekbote, Paul Pu Liang

机构 * MIT Media Lab（MIT媒体实验室）； MIT EECS（MIT电子工程与计算机科学系）

专题命中规划推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted as Oral at NeurIPS 2025. Revision after camera ready

2510.16916 2025-10-23 cs.LG 57%

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search

Dong Li, Xujiang Zhao, Linlin Yu, Yanchi Liu, Wei Cheng, Zhengzhang Chen, Zhong Chen, Feng Chen, Chen Zhao, Haifeng Chen

机构 * Baylor University（贝勒大学）； NEC Labs America（NEC美国实验室）； Augusta University（奥古斯塔大学）； Southern Illinois University（南方伊利诺伊大学）； University of Texas at Dallas（德克萨斯大学达拉斯分校）

专题命中规划推理：reasoning(abstract)；分类 cs.LG

Comments NeurIPS 2025

2507.15268 2025-10-23 cs.AI cs.MA 57%

IM-Chat: A Multi-agent LLM Framework Integrating Tool-Calling and Diffusion Modeling for Knowledge Transfer in Injection Molding Industry

Junhyeong Lee, Joon-Young Kim, Heekyu Kim, Inhyo Lee, Seunghwa Ryu

专题命中规划推理：reasoning(abstract)；分类 cs.AI

2510.19405 2025-10-23 cs.CY 50%

Designing Knowledge Tools: How Students Transition from Using to Creating Generative AI in STEAM classroom

Qian Huang, Nachamma Sockalingam, Thijs Willems, King Wang Poon

专题命中规划推理：planning(abstract)

Comments to be published in IEEE TALE 2025

2502.03158 2025-10-23 econ.GN q-fin.EC 50%

Strategizing with AI: Insights from a Beauty Contest Experiment

Iuliia Alekseenko, Dmitry Dagaev, Sofia Paklina, Petr Parshakov

专题命中规划推理：reasoning(abstract)

2510.19555 2025-10-23 cs.CV cs.CL 79%

[De|Re]constructing VLMs' Reasoning in Counting

Simone Alghisi, Gabriel Roccabruna, Massimo Rizzoli, Seyed Mahed Mousavi, Giuseppe Riccardi

机构 * University of Trento（特伦托大学）； Amazon（亚马逊公司）； SISLab（SIS实验室）； Department of Information Engineering and Computer Science（信息工程与计算机科学系）

专题命中视觉空间推理：reasoning(title,abstract)；分类 cs.CL

Comments This work has been submitted to the IEEE for possible publication

2510.19117 2025-10-23 cs.CL cs.LG eess.SP stat.ML 62%

A Graph Signal Processing Framework for Hallucination Detection in Large Language Models

Valentin Noël

机构 * Devoteam

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Preprint under review (2025). 11 pages, 7 figures. Code and scripts: to be released

2510.19031 2025-10-23 cs.HC cs.AI cs.CY 57%

CLiVR: Conversational Learning System in Virtual Reality with AI-Powered Patients

Akilan Amithasagaran, Sagnik Dakshit, Bhavani Suryadevara, Lindsey Stockton

机构 * The University of Texas at Tyler（德克萨斯理工大学）

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

2510.17830 2025-10-23 physics.app-ph cs.AI 57%

Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy

Meir H. Shachar, Dane M. Sterbentz, Harshitha Menon, Charles F. Jekel, M. Giselle Fernández-Godino, Nathan K. Brown, Ismael D. Boureima, Yue Hao, Kevin Korner, Robert Rieben, Daniel A. White, William J. Schill, Jonathan L. Belof

机构 * Sandia National Laboratories（桑迪亚国家实验室）； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

Comments Corrected the author's list metadata to match that found in the paper

2504.00939 2025-10-23 cs.CV cs.CL 57%

WikiVideo: Article Generation from Multiple Videos

Alexander Martin, Reno Kriz, William Gantt Walden, Kate Sanders, Hannah Recknor, Eugene Yang, Francis Ferraro, Benjamin Van Durme

机构 * Johns Hopkins University（约翰霍普金斯大学）； Human Language Technology Center of Excellence（人机语言技术卓越中心）； University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments Repo can be found here: https://github.com/alexmartin1722/wikivideo

2510.18179 2025-10-23 cs.MA 89%

Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning

Rui Jerry Huang, Wendy Liu, Anastasia Miin, Lei Ding

专题命中测试时计算：reasoning(title,abstract)；verifier(title,abstract)；self-correction(abstract)

Comments 13 pages, 8 figures. Accepted for presentation at the 5th Workshop on Mathematical Reasoning and AI at NeurIPS 2025

2508.00890 2025-10-23 cs.AI cs.CL cs.LG 82%

AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

Fali Wang, Hui Liu, Zhenwei Dai, Jingying Zeng, Zhiwei Zhang, Zongyu Wu, Chen Luo, Zhen Li, Xianfeng Tang, Qi He, Suhang Wang

机构 * The Pennsylvania State University（宾夕法尼亚州立大学）； Amazon（亚马逊）

专题命中测试时计算：test-time compute(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by NeurIPS 2025

2508.02511 2025-10-23 cs.AI cs.CL 73%

Test-time Prompt Intervention

Chenxu Yang, Qingyi Si, Mz Dai, Dingyu Yao, Mingyu Zheng, Minghui Chen, Zheng Lin, Weiping Wang

专题命中测试时计算：reasoning(abstract)；test-time compute(abstract)；分类 cs.CL、cs.AI

Comments 24 pages, 20 figures, under review

1. 数学推理 4 篇