大模型推理能力

ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning

Qizhi Pei, Zhuoshi Pan, Honglin Lin, Xin Gao, Yu Li, Zinan Tang, Conghui He, Rui Yan, Lijun Wu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学耿丽学校） ； OpenDataLab, Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Tsinghua University（清华大学） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） 纠错

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

Comments 15 pages

Reinforcement Learning on Pre-Training Data

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Evander Yang, Kun Li, Haoyuan Wu, Jiajia Wu, Zihao Zheng, Chenchen Zhang, Kun Shi, Kyrierl Deng, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang Xu, Zheng Fang, Shuai Li, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bo Chao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Wayyt Wang, Bo Zhou, Di Wang

机构 * LLM Department, Tencent（腾讯大模型部门） ； HunYuan Infra Team（文心一言基础设施团队） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Comments Work in progress

ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge

Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma, Hinrich Schütze

机构 * Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML）） 纠错

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

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It

Leonardo Bertolazzi, Philipp Mondorf, Barbara Plank, Raffaella Bernardi

机构 * DISI, University of Trento（特伦托大学DISI中心） ； MaiNLP, Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心） ； Munich Center for Machine Learning (MCML), Munich, Germany（慕尼黑机器学习中心） ； Free University of Bozen-Bolzano, Italy（博兹纳自由大学） 纠错

专题命中 数学推理 ：self-correction(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2025 Main, 38 pages, 33 figures

Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say

Jacob Fein-Ashley, Dhruv Parikh, Rajgopal Kannan, Viktor Prasanna

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

Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach

Yongda Yu, Guohao Shi, Xianwei Wu, Haochuan He, XueMing Gu, Qianqian Zhao, Kui Liu, Qiushi Wang, Zhao Tian, Haifeng Shen, Guoping Rong

机构 * Nanjing University（南京大学） ； University of Waterloo（滑铁卢大学） ； Northeastern University（东北大学） ； Huawei Technologies Co., Ltd.（华为技术有限公司） ； Southern Cross University（南方十字大学） 纠错

专题命中 逻辑推理 ：chain-of-thought(title,abstract)；reasoning(abstract)；CoT(abstract)；分类 cs.AI

Comments 22 pages

TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues

Yubin Ge, Salvatore Romeo, Jason Cai, Raphael Shu, Monica Sunkara, Yassine Benajiba, Yi Zhang

机构 * University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Amazon Web Services（亚马逊网络服务） 纠错

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

Comments Accepted at ACL 2025 Findings

R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning

Jiayi Lin, Liangcai Su, Junzhe Li, Chenxiong Qian

机构 * The University of Hong Kong（香港大学） 纠错

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

An Approach to Checking Correctness for Agentic Systems

Thomas J Sheffler

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

Comments 15 pages, 5 figures

Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering

Muhammad Fadhil Ginting, Dong-Ki Kim, Xiangyun Meng, Andrzej Reinke, Bandi Jai Krishna, Navid Kayhani, Oriana Peltzer, David D. Fan, Amirreza Shaban, Sung-Kyun Kim, Mykel J. Kochenderfer, Ali-akbar Agha-mohammadi, Shayegan Omidshafiei

机构 * Field AI Research Institute (FAIRI)（Field AI研究机构） ； Stanford University（斯坦福大学） 纠错

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

Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning

Milan Ganai, Rohan Sinha, Christopher Agia, Daniel Morton, Luigi Di Lillo, Marco Pavone

机构 * Stanford University（斯坦福大学） ； Swiss Re（瑞士再保险集团） ； NVIDIA Research（NVIDIA研究） 纠错

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

Comments Conference on Robot Learning (CoRL) 2025 (Oral)

SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation

Quang P. M. Pham, Khoi T. N. Nguyen, Nhi H. Doan, Cuong A. Pham, Qinbo Sun, Weimin Qi, Kentaro Inui, Dezhen Song

机构 * Department of Robotics, MBZUAI, UAE（机器人系，MBZUAI，阿联酋） 纠错

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

Comments Paper is under review

\LARGE GMP$^{3}$: Learning-Driven, Bellman-Guided Trajectory Planning for UAVs in Real-Time on SE(3)

Babak Salamat, Dominik Mattern, Sebastian-Sven Olzem, Gerhard Elsbacher, Christian Seidel, Andrea M. Tonello

专题命中 规划推理 ：planning(title,abstract)

Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinement

Jianbo Zhao, Taiyu Ban, Xiangjie Li, Xingtai Gui, Hangning Zhou, Lei Liu, Hongwei Zhao, Bin Li

机构 * University of Science and Technology of China（中国科学技术大学） ； Mach Drive（马车驱动） 纠错

专题命中 规划推理 ：planning(title,abstract)

Digital Twin-Guided Robot Path Planning: A Beta-Bernoulli Fusion with Large Language Model as a Sensor

Mani Amani, Reza Akhavian

机构 * Department of Civil, Construction, and Environmental Engineering, San Diego State University, San Diego, CA, United States（土木、建设与环境工程系，圣地亚哥州立大学，美国圣地亚哥，加利福尼亚州） ； Department of Electrical and Computer Engineering, University of California, San Diego, San Diego, CA, United States（电气与计算机工程系，加州大学圣地亚哥分校，美国圣地亚哥，加利福尼亚州） 纠错

专题命中 规划推理 ：planning(title,abstract)

AHA -- Predicting What Matters Next: Online Highlight Detection Without Looking Ahead

Aiden Chang, Celso De Melo, Stephanie M. Lukin

机构 * University of Southern California（南加州大学） ； DEVCOM Army Research Laboratory（陆军研究实验室） 纠错

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

Comments Accepted at NeurIPS 2025, 32 pages, 5 figures

Growing with Your Embodied Agent: A Human-in-the-Loop Lifelong Code Generation Framework for Long-Horizon Manipulation Skills

Yuan Meng, Zhenguo Sun, Max Fest, Xukun Li, Zhenshan Bing, Alois Knoll

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Comments update fig 1, typo correction - v2

ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspective

Yiwen Zhang, Ziang Chen, Fanqi Kong, Yizhe Huang, Xue Feng

机构 * State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； Peking University（北京大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Tsinghua University（清华大学） 纠错

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

Comments 22 pages, 14 figures

Safe Explicable Policy Search

Akkamahadevi Hanni, Jonathan Montaño, Yu Zhang

机构 * School of Computing and Augmented Intelligence, Arizona State University（计算与增强智能学院，亚利桑那州立大学） ； School of Mathematical and Statistical Sciences, Arizona State University（数学与统计科学学院，亚利桑那州立大学） 纠错

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

SwinMamba: A hybrid local-global mamba framework for enhancing semantic segmentation of remotely sensed images

Qinfeng Zhu, Han Li, Liang He, Lei Fan

专题命中 规划推理 ：planning(abstract)

Meta-Memory: Retrieving and Integrating Semantic-Spatial Memories for Robot Spatial Reasoning

Yufan Mao, Hanjing Ye, Wenlong Dong, Chengjie Zhang, Hong Zhang

机构 * Southern University of Science and Technology（南方科技大学） 纠错

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

3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering

Rongtao Xu, Han Gao, Mingming Yu, Dong An, Shunpeng Chen, Changwei Wang, Li Guo, Xiaodan Liang, Shibiao Xu

专题命中 视觉空间推理 ：reasoning(title,abstract)

Comments Accepted by IROS 2025

Cross-Modal Instructions for Robot Motion Generation

William Barron, Xiaoxiang Dong, Matthew Johnson-Roberson, Weiming Zhi

机构 * College of Connected Computing, Vanderbilt University（连接计算学院，范德比尔特大学） ； Robotics Institute, Carnegie Mellon University（机器人研究所，卡内基梅隆大学） ； School of Computer Science, The University of Sydney（计算机科学学院，悉尼大学） 纠错

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

GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutions

Bing Liu, Wenqiang Yv, Xuzheng Yang, Shichang Wang, Junzhuo Liu, Peng Wang, Guoqing Wang, Yang Yang, Heng Tao Shen

机构 * University of Electronic Science and Technology of China（电子科技大学） ； Tongji University（同济大学） 纠错

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

Human-like Navigation in a World Built for Humans

Bhargav Chandaka, Gloria X. Wang, Haozhe Chen, Henry Che, Albert J. Zhai, Shenlong Wang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments CoRL 2025. Project website: https://reasonnav.github.io/

Building Information Models to Robot-Ready Site Digital Twins (BIM2RDT): An Agentic AI Safety-First Framework

Reza Akhavian, Mani Amani, Johannes Mootz, Robert Ashe, Behrad Beheshti

机构 * Department of Civil, Construction, and Environmental Engineering, San Diego State University, San Diego, CA, United States（土木、建设与环境工程系，圣地亚哥州立大学） ； Department of Electrical and Computer Engineering, University of California, San Diego, San Diego, CA, United States（电气与计算机工程系，加州大学圣地亚哥分校） ； Department of Mechanical and Aerospace Engineering, University of California, San Diego, San Diego, CA, United States（机械与航空航天工程系，加州大学圣地亚哥分校） ； Department of Computer Science, San Diego State University, San Diego, CA, United States（计算机科学系，圣地亚哥州立大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

Jiaru Zou, Ling Yang, Jingwen Gu, Jiahao Qiu, Ke Shen, Jingrui He, Mengdi Wang

机构 * UIUC（伊利诺伊大学香槟分校） ； Princeton University（普林斯顿大学） ； Cornell University（康奈尔大学） ； ByteDance（字节跳动） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；chain-of-thought(title,abstract)；分类 cs.CL

Comments Accepted by NeurIPS 2025. Project: https://github.com/Gen-Verse/ReasonFlux

MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources

Sicong Leng, Jing Wang, Jiaxi Li, Hao Zhang, Zhiqiang Hu, Boqiang Zhang, Yuming Jiang, Hang Zhang, Xin Li, Lidong Bing, Deli Zhao, Wei Lu, Yu Rong, Aixin Sun, Shijian Lu

机构 * Nanyang Technological University（南洋理工大学） ； DAMO Academy, Alibaba Group（阿里巴巴集团达摩院） ； Singapore University of Technology and Design（新加坡科技设计大学） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)

Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute

Sheng Liu, Tianlang Chen, Pan Lu, Haotian Ye, Yizheng Chen, Lei Xing, James Zou

机构 * Stanford University（斯坦福大学） 纠错

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

Comments 18 pages, 5 figures, Project website: https://shengliu66.github.io/fractreason/

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

Yunheng Li, Jing Cheng, Shaoyong Jia, Hangyi Kuang, Shaohui Jiao, Qibin Hou, Ming-Ming Cheng

机构 * VCIP, School of Computer Science, Nankai University（VCIP，计算机科学学院，南开大学） ； ByteDance Inc.（字节跳动公司） 纠错

专题命中 测试时计算 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments Accepted at NeurIPS 2025