大模型推理能力

SWI: Speaking with Intent in Large Language Models

Yuwei Yin, EunJeong Hwang, Giuseppe Carenini

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Vector Institute for AI（人工智能矢量研究所） 纠错

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

Comments Code: https://github.com/YuweiYin/SWI

PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability

Tung Vu, Lam Nguyen, Quynh Dao

机构 * Posts and Telecommunications Institute of Technology（邮电技术研究所） ； Hanoi Architectural University（河内建筑大学） 纠错

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

Can Vision-Language Models Solve Visual Math Equations?

Monjoy Narayan Choudhury, Junling Wang, Yifan Hou, Mrinmaya Sachan

机构 * IIIT Bangalore（班加罗尔印度理工学院） ； ETH Zürich（苏黎世联邦理工学院） 纠错

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

Comments Monjoy Narayan Choudhury and Junling Wang contributed equally to this work. Accepted at EMNLP2025 main. Code and datasets are open-sourced with links in the paper

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing

All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens

Siddarth Mamidanna, Daking Rai, Ziyu Yao, Yilun Zhou

机构 * University of California, Santa Cruz（加州大学圣克鲁兹分校） ； George Mason University（乔治·马歇尔大学） ； Datadog AI Research（Datadog人工智能研究） 纠错

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

Comments EMNLP 2025 Main Conference

Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

Bohao Tang, Yan Ma, Fei Zhang, Jiadi Su, Ethan Chern, Zhulin Hu, Zhixin Wang, Pengfei Liu, Ya Zhang

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

A Logic for Expressing Log-Precision Transformers

William Merrill, Ashish Sabharwal

机构 * New York University（纽约大学） ； Allen Institute for AI（人工智能研究院） 纠错

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

Comments May 24, 2023: Restructured version of old preprint. Oct 12, 2023: To appear at NeurIPS. Sept 10, 2025: minor technical corrections

Robix: A Unified Model for Robot Interaction, Reasoning and Planning

Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li

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

Comments Tech report. Project page: https://robix-seed.github.io/robix/

AI Reasoning for Wireless Communications and Networking: A Survey and Perspectives

Haoxiang Luo, Yu Yan, Yanhui Bian, Wenjiao Feng, Ruichen Zhang, Yinqiu Liu, Jiacheng Wang, Gang Sun, Dusit Niyato, Hongfang Yu, Abbas Jamalipour, Shiwen Mao

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

Toward Generation of Test Cases from Task Descriptions via History-aware Planning

Duy Cao, Phu Nguyen, Vy Le, Tien N. Nguyen, Vu Nguyen

专题命中 规划推理 ：planning(title,abstract)

Comments Change the method and experimentation

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Haozhan Li, Yuxin Zuo, Jiale Yu, Yuhao Zhang, Zhaohui Yang, Kaiyan Zhang, Xuekai Zhu, Yuchen Zhang, Tianxing Chen, Ganqu Cui, Dehui Wang, Dingxiang Luo, Yuchen Fan, Youbang Sun, Jia Zeng, Jiangmiao Pang, Shanghang Zhang, Yu Wang, Yao Mu, Bowen Zhou, Ning Ding

机构 * Shanghai Jiao Tong University（上海交通大学） ； Peking University（北京大学） ； The University of Hong Kong（香港大学） ； Shanghai AI Lab（上海人工智能实验室） 纠错

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

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks

Andreas Happe, Jürgen Cito

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

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems

Minghang Zhu, Zhengliang Shi, Zhiwei Xu, Shiguang Wu, Lingjie Wang, Pengjie Ren, Zhaochun Ren, Zhumin Chen

机构 * Shandong University（山东大学） ； Leiden University（莱顿大学） 纠错

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

Comments EMNLP 2025 Findings

Resource-Efficient Glioma Segmentation on Sub-Saharan MRI

Freedmore Sidume, Oumayma Soula, Joseph Muthui Wacira, YunFei Zhu, Abbas Rabiu Muhammad, Abderrazek Zeraii, Oluwaseun Kalejaye, Hajer Ibrahim, Olfa Gaddour, Brain Halubanza, Dong Zhang, Udunna C Anazodo, Confidence Raymond

机构 * BAC School of Computing ； Information Systems, Botswana Faculty of Medicine of Sfax, University of Sfax, Sfax, Tunisia Laboratory of Biophysics ； Medical Technologies, Higher Institute of Medical Technologies of Tunis, University ElManar, Tunis, Tunisia London School of Hygiene ； Tropical Medicine, London, UK Lawson Health Research Institute, London, Ontario, Canada Department of Radiology, Bayero University, Kano-Nigeria Department of Radiology, Aminu Kano Teaching Hospital, Kano-Nigeria Department of Anatomy, Federal University Lokoja college of health sciences, Kogi State, Nigeria Department of Computer Science ； Information, College of Science, Majmaah University, AL-Majmaah, 11952, Saudi Arabia CES Laboratory, National School of Engineers of Sfax, Sfax, Tunisia Department of Computer Science ； IT, Mulungushi University, Zambia Multimodal Imaging of Neurodegenerative Diseases (MiND) Lab, Department of Neurology ； Neurosurgery, McGill University, Montreal, QC, Canada Department of Electrical ； Computer Engineering, University of British Columbia, Vancouver, Canada Medical Artificial Intelligence Laboratory (MAI Lab), Lagos, Nigeria Montreal Neurological Institute, McGill University, Montréal, Canada Department of Medicine, University of Cape Town, South Africa Department of Clinical \& Radiation Oncology, University of Cape Town, South Africa 纠错

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

Comments 11 pages, 7 figures

Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solving

Sanghyun Park, Boris Maciejovsky, Phanish Puranam

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

Comments 36 pages, 1 appendix

ProgD: Progressive Multi-scale Decoding with Dynamic Graphs for Joint Multi-agent Motion Forecasting

Xing Gao, Zherui Huang, Weiyao Lin, Xiao Sun

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Department of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学系） ； Department of Electronic Engineering, Shanghai Jiao Tong University（上海交通大学电子工程系） 纠错

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

Multi-Agent Vulcan: An Information-Driven Multi-Agent Path Finding Approach

Jake Olkin, Viraj Parimi, Brian Williams

专题命中 规划推理 ：planning(abstract)

Comments Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file

ObjectReact: Learning Object-Relative Control for Visual Navigation

Sourav Garg, Dustin Craggs, Vineeth Bhat, Lachlan Mares, Stefan Podgorski, Madhava Krishna, Feras Dayoub, Ian Reid

机构 * University of Adelaide, Australia（澳大利亚阿德莱德大学） ； IIIT Hyderabad, India（印度海得拉巴IIIT） ； MBZUAI, UAE（阿联酋MBZUAI） 纠错

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

Comments CoRL 2025; 23 pages including appendix

Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learning

Meng Feng, Viraj Parimi, Brian Williams

机构 * Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology（计算机科学与人工智能实验室，麻省理工学院） 纠错

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

Comments Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file

Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective

Bui Duc Manh, Soumyaratna Debnath, Zetong Zhang, Shriram Damodaran, Arvind Kumar, Yueyi Zhang, Lu Mi, Erik Cambria, Lin Wang

机构 * School of EEE, Nanyang Technological University（南洋理工大学电子工程系） ； Department of Civil Engineering, Tsinghua University（清华大学土木工程系） ； Dr. B. R. Ambedkar National Institute of Technology, Jalandhar（B.R.阿姆贝卡尔国家理工学院，贾兰德赫） ； KTH Royal Institute of Technology（皇家理工学院） ； College of AI, Tsinghua University（清华大学人工智能学院） ； CCDS, Nanyang Technological University（南洋理工大学CCDS） 纠错

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

Comments 54 pages, journal

CAME-AB: Cross-Modality Attention with Mixture-of-Experts for Antibody Binding Site Prediction

Hongzong Li, Jiahao Ma, Zhanpeng Shi, Rui Xiao, Fanming Jin, Ye-Fan Hu, Hangjun Che, Jian-Dong Huang

机构 * Generative AI Research and Development Center The Hong Kong University of Science and Technology（生成式人工智能研究与发展中心 香港科学大学） ； MILES The University of Hong Kong（MILES 香港大学） ； College of Veterinary Medicine Jilin University（吉林大学兽医学院） ； School of Chemistry and Chemical Engineering South China University of Technology（华南理工大学化学与化工学院） ； School of Biomedical Sciences The University of Hong Kong（香港大学生物医学科学学院） ； Computational Immunology Centre BayVax Biotech Limited（计算免疫学中心 BayVax 生物技术有限公司） ； College of Electronic and Information Engineering Southwest University（西南大学电子与信息工程学院） 纠错

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

Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models

Seungjae Lee, Daniel Ekpo, Haowen Liu, Furong Huang, Abhinav Shrivastava, Jia-Bin Huang

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

Comments Project webpage: https://ive-robot.github.io/

DATE: Dynamic Absolute Time Enhancement for Long Video Understanding

Chao Yuan, Yang Yang, Yehui Yang, Zach Cheng

机构 * Beihang University（北京航空航天大学） ； Dcar, ByteDance（字节跳动Dcar部门） ； Qfin Holdings,Inc（Qfin控股公司） ； MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院） 纠错

专题命中 测试时计算 ：reasoning(abstract)

MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction

Zhongqiu Li, Shiquan Wang, Ruiyu Fang, Mengjiao Bao, Zhenhe Wu, Shuangyong Song, Yongxiang Li, Zhongjiang He

机构 * Institute of Artificial Intelligence (TeleAI)（人工智能研究院） ； China Telecom Corp Ltd（中国电信有限公司） ； BeiHang University（北航大学） 纠错

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

Curriculum-Based Multi-Tier Semantic Exploration via Deep Reinforcement Learning

Abdel Hakim Drid, Vincenzo Suriani, Daniele Nardi, Abderrezzak Debilou

机构 * Department of Electrical Engineering - Mohamed Khider, University of Biskra, Biskra (Algeria)（巴尔克拉大学电子工程系） ； Department of Engineering - University of Basilicata, Potenza (Italy)（巴塞里卡大学工程系） ； Department of Computer, Control, and Management Engineering ``Antonio Ruberti'', Sapienza University of Rome, Rome (Italy)（罗马萨皮恩扎大学计算机、控制与管理工程系） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments The 19th International Conference on Intelligent Autonomous Systems (IAS 19), 2025, Genoa

Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs

Vaibhav Chaudhary, Neha Soni, Narotam Singh, Amita Kapoor

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments 46 pages, 4 figures, 17 tables

Visual Grounding from Event Cameras

Lingdong Kong, Dongyue Lu, Ao Liang, Rong Li, Yuhao Dong, Tianshuai Hu, Lai Xing Ng, Wei Tsang Ooi, Benoit R. Cottereau

机构 * NUS（新加坡国立大学） ； HKUST(GZ)（香港科技大学（广州）） ； NTU（南洋理工大学） ； HKUST（香港科技大学） ； I 2 R, A*STAR（新加坡科技研究局） ； IPAL, CNRS（法国国家科学研究中心IPAL） ； CerCo, CNRS（法国国家科学研究中心CerCo） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Abstract Paper (Non-Archival) @ ICCV 2025 NeVi Workshop

FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

Rongyao Fang, Aldrich Yu, Chengqi Duan, Linjiang Huang, Shuai Bai, Yuxuan Cai, Kun Wang, Si Liu, Xihui Liu, Hongsheng Li

机构 * CUHK（香港中文大学） ； HKU（香港大学） ； BUAA（北京航空航天大学） ； Alibaba（阿里巴巴） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments Project page: https://flux-reason-6m.github.io/

Optimizing Length Compression in Large Reasoning Models

Zhengxiang Cheng, Dongping Chen, Mingyang Fu, Tianyi Zhou

机构 * umd（马里兰大学） 纠错

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

Comments 16 pages, 7 figures, 4 tables

TreeGPT: Pure TreeFFN Encoder-Decoder Architecture for Structured Reasoning Without Attention Mechanisms

Zixi Li

机构 * Noesis Lab (Independent Research Group)（Noesis实验室（独立研究组）） ； Sun Yat-sen University（中山大学） 纠错

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

Comments Code available at: https://github.com/lizixi-0x2F/TreeGPT

Culturally-Nuanced Story Generation for Reasoning in Low-Resource Languages: The Case of Javanese and Sundanese

Salsabila Zahirah Pranida, Rifo Ahmad Genadi, Fajri Koto

机构 * Department of Natural Language Processing, MBZUAI（自然语言处理系，MBZUAI） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；分类 cs.CL