大模型推理能力

DSADF: Thinking Fast and Slow for Decision Making

Zhihao Dou, Dongfei Cui, Jun Yan, Weida Wang, Benteng Chen, Haoming Wang, Zeke Xie, Shufei Zhang

机构 * Pratt School of Engineering（普拉特工程学院） ； Duke University（杜克大学） ； School of Computer Science（计算机科学学院） ； Northeast Electric Power University（东北电力大学） ； Department of Information and Communication Engineering（信息与通信工程系） ； Tongji University（同济大学） ； School of Computer Science and Technology（计算机科学与技术学院） ； School of International Education（国际教育学院） ； Beijing University of Chemical Technology（北京化工大学） ； East China Normal University（华东师范大学） ； Information Hub（信息枢纽） ； Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Chinese Academy of Science（中国科学院） 纠错

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

Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective

Tianyao Shi, Yi Ding

机构 * Purdue University（普渡大学） 纠错

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

Comments 14 pages, 10 figures, 4 tables

Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think Slow

Y. Du, C. Guo, W. Wang, G. Tang

机构 * Independent Researchers（独立研究者） 纠错

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

Comments 6 pages

Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization

Mohammad J. Abdel-Rahman, Yasmeen Alslman, Dania Refai, Amro Saleh, Malik A. Abu Loha, Mohammad Yahya Hamed

机构 * Data Science Department, Princess Sumaya University for Technology（普里姆斯萨大学技术学院数据科学系） ； Electrical and Computer Engineering Department, Virginia Tech（弗吉尼亚理工大学电气与计算机工程系） ； Computer Science Department, Princess Sumaya University for Technology（普里姆斯萨大学技术学院计算机科学系） ； Computer Science Department, King Fahd University of Petroleum and Minerals（国王法赫德石油与矿物大学计算机科学系） 纠错

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

Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding

Pu Feng, Size Wang, Yuhong Cao, Junkang Liang, Rongye Shi, Wenjun Wu

机构 * 1State Key Laboratory of Complex \& Critical Software Environment, Beihang University, Beijing, China ； 2School of Artificial Intelligence, Beihang University, Beijing, China ； 3Hangzhou International Innovation Institute, Hangzhou, China ； 4Department of Mechanical Engineering, National University of Singapore, Singapore 纠错

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

Comments Accepted by IJCNN 2025

Citizen Centered Climate Intelligence: Operationalizing Open Tree Data for Urban Cooling and Eco-Routing in Indian Cities

Kaushik Ravi, Andreas Brück

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

Comments Forthcoming book chapter, currently under review for the "HackYourDistrict" initiative at TU Berlin. 20 pages, 9 figures, 1 table

Chinese Court Simulation with LLM-Based Agent System

Kaiyuan Zhang, Jiaqi Li, Yueyue Wu, Haitao Li, Cheng Luo, Shaokun Zou, Yujia Zhou, Weihang Su, Qingyao Ai, Yiqun Liu

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

Rethinking How AI Embeds and Adapts to Human Values: Challenges and Opportunities

Sz-Ting Tzeng, Frank Dignum

机构 * Ume University（乌梅大学） 纠错

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

Comments 7 pages, accepted at VALE 2025

Improving Table Understanding with LLMs and Entity-Oriented Search

Thi-Nhung Nguyen, Hoang Ngo, Dinh Phung, Thuy-Trang Vu, Dat Quoc Nguyen

机构 * Monash University（莫纳什大学） ； Qualcomm AI Research（高通人工智能研究） 纠错

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

Comments Accepted to COLM 2025

DecisionFlow: Advancing Large Language Model as Principled Decision Maker

Xiusi Chen, Shanyong Wang, Cheng Qian, Hongru Wang, Peixuan Han, Heng Ji

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

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

Comments EMNLP 2025 Findings; 25 pages, 15 figures

MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation

Harsh Singh, Rocktim Jyoti Das, Mingfei Han, Preslav Nakov, Ivan Laptev

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

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

Comments 48 pages

RoboBuddy in the Classroom: Exploring LLM-Powered Social Robots for Storytelling in Learning and Integration Activities

Daniel Tozadore, Nur Ertug, Yasmine Chaker, Mortadha Abderrahim

机构 * Computer-Human Interaction in Learning and Instruction (CHILI) Lab, EPFL, Lausanne, Switzerland（计算机-人类交互在学习与教学（CHILI）实验室，EPFL，拉沃斯，瑞士） ； Depart of Computer Science of the University College London, London, UK（大学学院伦敦计算机科学系，伦敦，英国） 纠错

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

Comments Accepted to be published in the proceedings of 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) in 2025

InReAcTable: LLM-Powered Interactive Visual Data Story Construction from Tabular Data

Gerile Aodeng, Guozheng Li, Yunshan Feng, Qiyang Chen, Yu Zhang, Chi Harold Liu

专题命中 规划推理 ：reasoning(abstract)

Comments 16 pages, 10 figures, accepted at ACM UIST 2025 (to appear)

An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image Editing

Zihan Liang, Jiahao Sun, Haoran Ma

机构 * Kunming University of Science and Technology（昆明理工大学） 纠错

专题命中 规划推理 ：planning(abstract)

FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real

Weiheng Liu, Yuxuan Wan, Jilong Wang, Yuxuan Kuang, Wenbo Cui, Xuesong Shi, Haoran Li, Dongbin Zhao, Zhizheng Zhang, He Wang

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； CFCS, School of Computer Science, Peking University（计算机科学系，北京大学） ； Galbot ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） 纠错

专题命中 规划推理 ：planning(abstract)

Comments 9th Annual Conference on Robot Learning (CoRL 2025, Oral)

Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning

Junhao Wu, Yun Li, Junhao Li, Jingliang Bian, Xiaomao Fan, Wenbin Lei, Ruxin Wang

机构 * Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院） ； First Affiliated Hospital, Sun Yat-sen University（中山大学第一附属医院） ； College of Big Data and Internet, Shenzhen Technology University（深圳技术大学大数据与互联网学院） 纠错

专题命中 规划推理 ：planning(abstract)

Comments 12 pages,6 figures, 6 tables

Baltimore Atlas: FreqWeaver Adapter for Semi-supervised Ultra-high Spatial Resolution Land Cover Classification

Junhao Wu, Aboagye-Ntow Stephen, Chuyuan Wang, Gang Chen, Xin Huang

机构 * Towson University（托逊大学） ； University of North Carolina at Charlotte（北卡罗来纳州夏洛特大学） 纠错

专题命中 规划推理 ：planning(abstract)

ArgusCogito: Chain-of-Thought for Cross-Modal Synergy and Omnidirectional Reasoning in Camouflaged Object Segmentation

Jianwen Tan, Huiyao Zhang, Rui Xiong, Han Zhou, Hongfei Wang, Ye Li

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间利用技术与工程中心） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；chain-of-thought(title,abstract)

Multi-Agent Visual-Language Reasoning for Comprehensive Highway Scene Understanding

Yunxiang Yang, Ningning Xu, Jidong J. Yang

机构 * Smart Mobility and Infrastructure Lab（智能移动与基础设施实验室） ； College of Engineering, University of Georgia（佐治亚大学工程学院） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments 16 pages, 16 figures, 8 tables

Robust Diagram Reasoning: A Framework for Enhancing LVLM Performance on Visually Perturbed Scientific Diagrams

Minghao Zhou, Rafael Souza, Yaqian Hu, Luming Che

机构 * Taiyuan University of Science and Technology（太原科技大学） ； University of Brasilia（巴西利亚大学） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；self-correction(abstract)

TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints

Vinh-Thuan Ly, Hoang M. Truong, Xuan-Huong Nguyen

机构 * University of Science, VNU-HCM（越南胡志明市国家大学） ； Vietnam National University（越南国家大学） 纠错

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

Comments Accepted for presentation at the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025

Journal ref IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, Hawaii, 2025

An Embodied AR Navigation Agent: Integrating BIM with Retrieval-Augmented Generation for Language Guidance

Hsuan-Kung Yang, Tsu-Ching Hsiao, Ryoichiro Oka, Ryuya Nishino, Satoko Tofukuji, Norimasa Kobori

机构 * Woven by Toyota, Inc., Japan（丰田公司，日本） 纠错

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

Comments 11 pages, 9 figures, accepted to IEEE ISMAR 2025

From reactive to cognitive: brain-inspired spatial intelligence for embodied agents

Shouwei Ruan, Liyuan Wang, Caixin Kang, Qihui Zhu, Songming Liu, Xingxing Wei, Hang Su

机构 * Department of Computer Science and Technology, Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab（计算机科学与技术系、人工智能研究院、BNRist中心、清华-博世联合机器学习中心、THBI实验室） ； Institute of Artificial Intelligence（人工智能研究院） ； Department of Psychological and Cognitive Sciences（心理学与认知科学系） 纠错

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

Comments 40 pages, 8 figures

Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding

Leilei Guo, Antonio Carlos Rivera, Peiyu Tang, Haoxuan Ren, Zheyu Song

机构 * Zhongkai University of Agriculture and Engineering（仲恺农业工程大学） ； EDP University of Puerto Rico: San Sebastian（波多黎各圣塞巴斯蒂安EDP大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions

Ziming Cheng, Zhiyuan Huang, Junting Pan, Zhaohui Hou, Mingjie Zhan

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； SenseTime Research（商汤科技研究院） ； MMLab, CUHK（CUHK的MMLab） 纠错

专题命中 视觉空间推理 ：self-correction(abstract)

Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles

Jiangfan Liu, Yongkang Guo, Fangzhi Zhong, Tianyuan Zhang, Zonglei Jing, Siyuan Liang, Jiakai Wang, Mingchuan Zhang, Aishan Liu, Xianglong Liu

机构 * Beihang University（北京航空航天大学） ； Nanyang Technological University（南洋理工大学） ； Zhongguancun Laboratory（中关村实验室） ； Henan University of Science and Technology（河南科技大学） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs

Qianqi Yan, Hongquan Li, Shan Jiang, Yang Zhao, Xinze Guan, Ching-Chen Kuo, Xin Eric Wang

机构 * University of California, Santa Cruz（加州大学圣克鲁兹分校） ； eBay 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.AI

QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso

机构 * JP Morgan AI Research（摩根大通人工智能研究） 纠错

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

Yizhi Li, Qingshui Gu, Zhoufutu Wen, Ziniu Li, Tianshun Xing, Shuyue Guo, Tianyu Zheng, Xin Zhou, Xingwei Qu, Wangchunshu Zhou, Zheng Zhang, Wei Shen, Qian Liu, Chenghua Lin, Jian Yang, Ge Zhang, Wenhao Huang

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL、cs.LG

Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation

Kaidong Feng, Zhu Sun, Hui Fang, Jie Yang, Wenyuan Liu, Yew-Soon Ong

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL