大模型推理能力

Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning

Sara Rajaee, Rochelle Choenni, Ekaterina Shutova, Christof Monz

机构 * Language Technology Lab, University of Amsterdam（阿姆斯特丹大学语言技术实验室） ； ILLC, University of Amsterdam（阿姆斯特丹大学语言学研究所） 纠错

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

Mind the Gap: Data Rewriting for Stable Off-Policy Supervised Fine-Tuning

Shiwan Zhao, Xuyang Zhao, Jiaming Zhou, Aobo Kong, Qicheng Li, Yong Qin

机构 * College of Computer Science, Nankai University（南开大学计算机科学学院） 纠错

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

DebFlow: Automating Agent Creation via Agent Debate

Jinwei Su, Yinghui Xia, Yiqun Duan, Jun Du, Jianuo Huang, Tianyu Shi, Lewei He

机构 * School of Artificial Intelligence, South China Normal University（人工智能学院，华南师范大学） ； University of Toronto（多伦多大学） 纠错

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

Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semantics

Reza Sanayei, Srdjan Vesic, Eduardo Blanco, Mihai Surdeanu

机构 * Department of Computer Science, University of Arizona（亚利桑那大学计算机科学系） ； CRIL CNRS & University of Artois（CNRS CRIL与阿维尼昂大学） 纠错

专题命中 代码与定理证明 ：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2025 Findings

MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning

Jugal Gajjar, Kamalasankari Subramaniakuppusamy, Noha El Kachach

机构 * Computer Science Department（计算机科学系） ； The George Washington University（乔治华盛顿大学） 纠错

专题命中 代码与定理证明 ：reasoning(title,abstract)；分类 cs.AI

Comments 6 pages, 4 figures, accepted for publication in IEEE 26th International Conference on Information Reuse and Integration (IRI 2025)

Emulating Public Opinion: A Proof-of-Concept of AI-Generated Synthetic Survey Responses for the Chilean Case

Bastián González-Bustamante, Nando Verelst, Carla Cisternas

机构 * Universidad Diego Portales（迪亚戈·波特莱斯大学） ； Leiden University（莱顿大学） 纠错

专题命中 代码与定理证明 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Working paper: 18 pages, 4 tables, 2 figures

Journal ref Empiria Lab Method Series (2025)

FLARE: Faithful Logic-Aided Reasoning and Exploration

Erik Arakelyan, Pasquale Minervini, Pat Verga, Patrick Lewis, Isabelle Augenstein

机构 * University of Copenhagen（哥本哈根大学） ； University of Edinburgh（爱丁堡大学） ； Cohere ； NVIDIA 纠错

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

Comments Published at EMNLP 2025

SPaRC: A Spatial Pathfinding Reasoning Challenge

Lars Benedikt Kaesberg, Jan Philip Wahle, Terry Ruas, Bela Gipp

专题命中 逻辑推理 ：reasoning(title,abstract)；planning(abstract)；test-time compute(abstract)；分类 cs.CL、cs.AI

Comments Accepted at EMNLP 2025 (Main)

Journal ref EMNLP 2025

MicroRCA-Agent: Microservice Root Cause Analysis Method Based on Large Language Model Agents

Pan Tang, Shixiang Tang, Huanqi Pu, Zhiqing Miao, Zhixing Wang

机构 * School of Communication and Information Engineering, Shanghai University, Shanghai, China（上海大学通信与信息工程学院） ； School of Communication and Electronic Engineering, East China Normal University, Shanghai, China（华东师范大学通信与电子工程学院） ； School of Information and Electronics, Beijing Institute of Technology, Beijing, China（北京理工大学信息与电子学院） 纠错

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

Comments 18 pages, 22 figures

FSLI: An Interpretable Formal Semantic System for One-Dimensional Ordering Inference

Maha Alkhairy, Vincent Homer, Brendan O'Connor

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） 纠错

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

Comments 3 figures, 9 pages main paper and 8 pages references and appendix

SMART: Scalable Multi-Agent Reasoning and Trajectory Planning in Dense Environments

Heye Huang, Yibin Yang, Wang Chen, Tiantian Chen, Xiaopeng Li, Sikai Chen

机构 * Department of Civil and Environmental Engineering University of Wisconsin-Madison（威斯康星大学麦迪逊分校土木与环境工程系） ； School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动性学院） ； Department of Civil Engineering, The University of Hong Kong（香港大学土木工程系） 纠错

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

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

Yaorui Shi, Sihang Li, Chang Wu, Zhiyuan Liu, Junfeng Fang, Hengxing Cai, An Zhang, Xiang Wang

机构 * University of Science and Technology of China（中国科学技术大学） ； National University of Singapore（新加坡国立大学） ； DP Technology（DP技术） 纠错

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

Can AI with High Reasoning Ability Replicate Human-like Decision Making in Economic Experiments?

Ayato Kitadai, Sinndy Dayana Rico Lugo, Yudai Tsurusaki, Yusuke Fukasawa, Nariaki Nishino

专题命中 规划推理 ：reasoning(title,abstract)

Comments 10 pages, 5 figures

Towards Interactive and Learnable Cooperative Driving Automation: a Large Language Model-Driven Decision-Making Framework

Shiyu Fang, Jiaqi Liu, Mingyu Ding, Yiming Cui, Chen Lv, Peng Hang, Jian Sun

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

Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds

Remo Sasso, Michelangelo Conserva, Dominik Jeurissen, Paulo Rauber

机构 * School of Electronic Engineering and Computer Science（电子工程与计算机科学学院） 纠错

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

Comments 20 pages, 9 figures. Accepted for presentation at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop on Embodied World Models for Decision Making

MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling

Zhaopeng Feng, Jiahan Ren, Jiayuan Su, Jiamei Zheng, Hongwei Wang, Zuozhu Liu

机构 * Zhejiang University（浙江大学） 纠错

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

Comments EMNLP 2025 Findings. Project page:https://sabijun.github.io/MT_RewardTreePage

Language-Based Bayesian Optimization Research Assistant (BORA)

Abdoulatif Cissé, Xenophon Evangelopoulos, Vladimir V. Gusev, Andrew I. Cooper

机构 * Department of Chemistry, University of Liverpool, England, UK（利物浦大学化学系） ； Leverhulme Research Centre for Functional Materials Design, University of Liverpool, England, UK（利物浦大学功能材料设计研究所以） ； Department of Computer Science, University of Liverpool, England, UK（利物浦大学计算机科学系） 纠错

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

Journal ref IJCAI-25: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, pp. 4967-4975 (2025)

Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification

Ming Hu, Jianfu Yin, Mingyu Dou, Yuqi Wang, Ruochen Dang, Siyi Liang, Feiyu Zhu, Cong Hu, Yao Wang, Bingliang Hu, Quan Wang

机构 * Xi’an Institute of Optics and Precision Mechanics, CAS（西安光学精密机械研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Southwest Jiaotong University（西南交通大学） ； Zhongnan Hospital of Wuhan University（武汉大学中南医院） ； Xi’an Jiaotong University（西安交通大学） ； National Key Laboratory of Information Systems Engineering（信息系统工程国家重点实验室） 纠错

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

Coordinated Multi-Drone Last-mile Delivery: Learning Strategies for Energy-aware and Timely Operations

Chuhao Qin, Arun Narayanan, Evangelos Pournaras

机构 * School of Computer Science, University of Leeds, UK（计算机科学学院，利兹大学，英国） ； School of Energy Systems, LUT University, Finland（能源系统学院，卢霍斯大学，芬兰） 纠错

专题命中 规划推理 ：planning(abstract)

Comments 12 pages, 8 figures. This work has been submitted to the IEEE for possible publication

Dynamic Agent Grouping ECBS: Scaling Windowed Multi-Agent Path Finding with Completeness Guarantees

Tiannan Zhang, Rishi Veerapaneni, Shao-Hung Chan, Jiaoyang Li, Maxim Likhachev

专题命中 规划推理 ：planning(abstract)

Data-Efficient Learning for Generalizable Surgical Video Understanding

Sahar Nasirihaghighi

机构 * Department of Information Technology (ITEC), University of Klagenfurt（信息科技系，克雷根弗特大学） 纠错

专题命中 规划推理 ：planning(abstract)

Integrating Spatiotemporal Vision Transformer into Digital Twins for High-Resolution Heat Stress Forecasting in Campus Environments

Wenjing Gong, Xinyue Ye, Keshu Wu, Suphanut Jamonnak, Wenyu Zhang, Yifan Yang, Xiao Huang

专题命中 规划推理 ：planning(abstract)

Comments Revised version after peer review (minor revision)

SmolRGPT: Efficient Spatial Reasoning for Warehouse Environments with 600M Parameters

Abdarahmane Traore, Éric Hervet, Andy Couturier

机构 * Embia, Computer Science Department, Faculty of Science, Université de Moncton（Embia计算机科学系，科学学院，蒙特龙大学） 纠错

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

Comments 9 pages, 3 figures, IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

Causal Reasoning Elicits Controllable 3D Scene Generation

Shen Chen, Ruiyu Zhao, Jiale Zhou, Zongkai Wu, Jenq-Neng Hwang, Lei Li

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

See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model

Pengteng Li, Pinhao Song, Wuyang Li, Weiyu Guo, Huizai Yao, Yijie Xu, Dugang Liu, Hui Xiong

机构 * HKUST(GZ)（香港科技大学（广州）） ； KU Leuven（比利时鲁文大学） ； EPFL（苏黎世联邦理工学院） ； SZU（深圳大学） 纠错

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

Comments Accepted by NeurIPS 2025

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data

Haoyu Zhang, Meng Liu, Zaijing Li, Haokun Wen, Weili Guan, Yaowei Wang, Liqiang Nie

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） ； Pengcheng Laboratory（鹏城实验室） ； Shandong Jianzhu University（山东建筑大学） 纠错

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

Comments Accepted by NeurIPS 2025 as a Spotlight

Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation

Weimin Bai, Yubo Li, Weijian Luo, Wenzheng Chen, He Sun

机构 * Peking University（北京大学） ； Xiaohongshu Inc（小红书公司） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Imagination at Inference: Synthesizing In-Hand Views for Robust Visuomotor Policy Inference

Haoran Ding, Anqing Duan, Zezhou Sun, Dezhen Song, Yoshihiko Nakamura

机构 * Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（机器人系，Mohamed bin Zayed人工智能大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Submitted to IEEE for possible publication, under review

Affordance-Based Disambiguation of Surgical Instructions for Collaborative Robot-Assisted Surgery

Ana Davila, Jacinto Colan, Yasuhisa Hasegawa

机构 * Nagoya University, Japan（名古屋大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments To be presented at the 1st Workshop on Intelligent Cobodied Assistance and Robotic Empowerment (iCARE). 2025 Conference on Robot Learning (CoRL)

World Modelling Improves Language Model Agents

Shangmin Guo, Omar Darwiche Domingues, Raphaël Avalos, Aaron Courville, Florian Strub

机构 * University of Edinburgh（爱丁堡大学） ； Cohere ； Vrije Universiteit Brussel（布鲁塞尔自由大学） ； Université de Montréal（蒙特利尔大学） 纠错

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