大模型推理能力

Development of Mental Models in Human-AI Collaboration: A Conceptual Framework

Joshua Holstein, Gerhard Satzger

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

Comments Preprint version. Accepted for presentation at the International Conference on Information Systems (ICIS 2025). Please cite the published version when available

Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines

Amine Barrak

机构 * Department of Computer Science and Engineering（计算机科学与工程系） ； Oakland University（奥克兰大学） 纠错

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

Journal ref 2025 40th ACM/IEEE International Conference on Automated Software Engineering Workshops

Towards Urban Planing AI Agent in the Age of Agentic AI

Rui Liu, Tao Zhe, Zhong-Ren Peng, Necati Catbas, Xinyue Ye, Dongjie Wang, Yanjie Fu

机构 * University of Kansas（堪萨斯大学） ； University of Florida（佛罗里达大学） ； University of Central Florida（中央佛罗里达大学） ； University of Alabama（阿拉巴马大学） ； Arizona State University（亚利桑那州立大学） 纠错

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

Comments this more comprehensive version is under reviewed in ACM SIGKDD exploration

Mephisto: Self-Improving Large Language Model-Based Agents for Automated Interpretation of Multi-band Galaxy Observations

Zechang Sun, Yuan-Sen Ting, Yaobo Liang, Nan Duan, Song Huang, Zheng Cai

专题命中 规划推理 ：reasoning(abstract)

Comments 17 pages main text + 13 pages appendix. A conference abstract is available at arXiv:2409.14807. Submitted to AAS journal. Comments and feedback are welcome!

Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing

Zhentao Zou, Zhengrong Yue, Kunpeng Du, Binlei Bao, Hanting Li, Haizhen Xie, Guozheng Xu, Yue Zhou, Yali Wang, Jie Hu, Xue Jiang, Xinghao Chen

机构 * Shanghai Jiaotong University（上海交通大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； East China Normal University（华东师范大学） ； Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院） 纠错

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

Comments 25pages,20figures

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models

Hongxing Li, Dingming Li, Zixuan Wang, Yuchen Yan, Hang Wu, Wenqi Zhang, Yongliang Shen, Weiming Lu, Jun Xiao, Yueting Zhuang

机构 * Zhejiang University（浙江大学） 纠错

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

Comments Project Page: https://zju-real.github.io/SpatialLadder/ Code: https://github.com/ZJU-REAL/SpatialLadder

To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models

Jiayun Luo, Wan-Cyuan Fan, Lyuyang Wang, Xiangteng He, Tanzila Rahman, Purang Abolmaesumi, Leonid Sigal

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 视觉空间推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Preprint. Project page: https://davidhalladay.github.io/diysink_demo

Play to Generalize: Learning to Reason Through Game Play

Yunfei Xie, Yinsong Ma, Shiyi Lan, Alan Yuille, Junfei Xiao, Chen Wei

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

Comments Project Page: https://yunfeixie233.github.io/ViGaL/

ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation

Haitao Jia, Ming He, Zimo Yin, Likang Wu, Jianping Fan, Jitao Sang

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

An LLM-Powered Cooperative Framework for Large-Scale Multi-Vehicle Navigation

Yuping Zhou, Siqi Lai, Jindong Han, Hao Liu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） 纠错

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

LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement Learning

Yuhan Sun, Zhiwei Huang, Wanqing Cui, Shaopan Xiong, Yazhi Guo, Meiguang Jin, Junfeng Ma

机构 * Taobao \& Tmall Group of Alibaba Hangzhou Zhejiang China ； Taobao \& Tmall Group of Alibaba Beijing China ； ROLL Team of Alibaba Hangzhou Zhejiang China ； Taobao \& Tmall Group of Alibaba ； ROLL Team of Alibaba 纠错

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

Comments 12 pages, 8 figures

Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models

Đorđe Klisura, Joseph Khoury, Ashish Kundu, Ram Krishnan, Anthony Rios

机构 * University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校） ； Louisiana State University（路易斯安那州立大学） ； Cisco Research（思科研究） 纠错

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

Comments 8 pages + Appendix

Can Speech LLMs Think while Listening?

Yi-Jen Shih, Desh Raj, Chunyang Wu, Wei Zhou, SK Bong, Yashesh Gaur, Jay Mahadeokar, Ozlem Kalinli, Mike Seltzer

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Meta Superintelligence Labs（Meta超智能实验室） 纠错

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

Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling

Jannek Ulm, Kevin Du, Vésteinn Snæbjarnarson

机构 * ETH Zürich（苏黎世联邦理工学院） ； University of Copenhagen（哥本哈根大学） 纠错

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

Comments 13 pages, 3 figures

OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs

Jaeseong Lee, seung-won hwang, Aurick Qiao, Gabriele Oliaro, Ye Wang, Samyam Rajbhandari

机构 * Snowflake AI Research（Snowflake AI研究院） ； Seoul National University（首尔国立大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

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

AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming

Muxi Diao, Yutao Mou, Keqing He, Hanbo Song, Lulu Zhao, Shikun Zhang, Wei Ye, Kongming Liang, Zhanyu Ma

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Peking University（北京大学） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） 纠错

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

FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion

Zhanqiu Hu, Jian Meng, Yash Akhauri, Mohamed S. Abdelfattah, Jae-sun Seo, Zhiru Zhang, Udit Gupta

机构 * Cornell University（康奈尔大学） 纠错

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

A Survey of Reinforcement Learning for Large Reasoning Models

Kaiyan Zhang, Yuxin Zuo, Bingxiang He, Youbang Sun, Runze Liu, Che Jiang, Yuchen Fan, Kai Tian, Guoli Jia, Pengfei Li, Yu Fu, Xingtai Lv, Yuchen Zhang, Sihang Zeng, Shang Qu, Haozhan Li, Shijie Wang, Yuru Wang, Xinwei Long, Fangfu Liu, Xiang Xu, Jiaze Ma, Xuekai Zhu, Ermo Hua, Yihao Liu, Zonglin Li, Huayu Chen, Xiaoye Qu, Yafu Li, Weize Chen, Zhenzhao Yuan, Junqi Gao, Dong Li, Zhiyuan Ma, Ganqu Cui, Zhiyuan Liu, Biqing Qi, Ning Ding, Bowen Zhou

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

Comments Fixed typos; added missing and recent citations (117 -> 120 pages)

STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models

Kyumin Lee, Minjin Jeon, Sanghwan Jang, Hwanjo Yu

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

Comments EMNLP 2025 Main

Learning to Reason for Hallucination Span Detection

Hsuan Su, Ting-Yao Hu, Hema Swetha Koppula, Kundan Krishna, Hadi Pouransari, Cheng-Yu Hsieh, Cem Koc, Joseph Yitan Cheng, Oncel Tuzel, Raviteja Vemulapalli

机构 * National Taiwan University（国立台湾大学） ； Apple（苹果公司） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

First Try Matters: Revisiting the Role of Reflection in Reasoning Models

Liwei Kang, Yue Deng, Yao Xiao, Zhanfeng Mo, Wee Sun Lee, Lidong Bing

机构 * MiroMind AI ； National University of Singapore（新加坡国立大学） ； Singapore University of Technology and Design（新加坡科技设计大学） 纠错

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

SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models

Huahui Yi, Kun Wang, Qiankun Li, Miao Yu, Liang Lin, Gongli Xi, Hao Wu, Xuming Hu, Kang Li, Yang Liu

机构 * West China Biomedical Big Data Center, West China Hospital, SCU（西昌生物医学大数据中心、西昌医院、SCU） ； NTU ； USTC ； TeleAI, China Telecom（TeleAI、中国电信） ； BUPT ； Tsinghua University（清华大学） ； HKUST(Guangzhou)（HKUST（广州）） 纠错

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

IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction

Yandu Chen, Kefan Gu, Yuqing Wen, Yucheng Zhao, Tiancai Wang, Liqiang Nie

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） ； Nanjing University（南京大学） ； University of Science and Technology of China（中国科学技术大学） ； Dexmal 纠错

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

SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning

Peixian Ma, Xialie Zhuang, Chengjin Xu, Xuhui Jiang, Ran Chen, Jian Guo

专题命中 复杂问题求解 ：reasoning(title,abstract)

Comments Accepd by NeurIPS 2025

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning

Cheng Qian, Zuxin Liu, Shirley Kokane, Akshara Prabhakar, Jielin Qiu, Haolin Chen, Zhiwei Liu, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang

机构 * Salesforce AI Research（Salesforce AI研究院） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments 24 Pages, 4 Figures, 2 Tables

Understanding In-context Learning of Addition via Activation Subspaces

Xinyan Hu, Kayo Yin, Michael I. Jordan, Jacob Steinhardt, Lijie Chen

机构 * UC Berkeley（伯克利大学） ； INRIA（法国国家信息与自动化研究所） 纠错

专题命中 复杂问题求解 ：self-correction(abstract)；分类 cs.CL、cs.AI、cs.LG

GCPO: When Contrast Fails, Go Gold

Hao Wu, Wei Liu

机构 * Tencent（腾讯） 纠错

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

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Ang Li, Charles Wang, Deqing Fu, Kaiyu Yue, Zikui Cai, Wang Bill Zhu, Ollie Liu, Peng Guo, Willie Neiswanger, Furong Huang, Tom Goldstein, Micah Goldblum

机构 * Columbia University（哥伦比亚大学） ； University of Maryland（马里兰大学） ； University of Southern California（南加州大学） ； New York University（纽约大学） 纠错

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

Comments dataset link: https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning

Yu Sun, Xingyu Qian, Weiwen Xu, Hao Zhang, Chenghao Xiao, Long Li, Deli Zhao, Wenbing Huang, Tingyang Xu, Qifeng Bai, Yu Rong

机构 * Alibaba DAMO Academy（阿里巴巴达摩院） ； School of Basic Medical Sciences, Lanzhou University（兰州大学基础医学学院） ； Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学光荣人工智能学院） ； Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大型模型与智能治理研究重点实验室） ； Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（教育部下一代智能搜索与推荐工程研究中心） 纠错

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

Comments 28 pages, 6 figures, 7 tables

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models

Andong Deng, Taojiannan Yang, Shoubin Yu, Lincoln Spencer, Mohit Bansal, Chen Chen, Serena Yeung-Levy, Xiaohan Wang

机构 * University of Central Florida（中央佛罗里达大学） ； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Stanford University（斯坦福大学） 纠错

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