大模型推理能力

Cognitive Biases in LLM-Assisted Software Development

大语言模型辅助软件开发中的认知偏差

Xinyi Zhou, Zeinadsadat Saghi, Sadra Sabouri, Rahul Pandita, Mollie McGuire, Souti Chattopadhyay

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

AI总结 本文研究了大语言模型辅助软件开发中的认知偏差，通过混合方法分析发现LLM相关行动更易产生新型偏差，并提出15种偏差类别及缓解建议。

Comments 13 pages, 6 figures, 7 tables

On Angels and Demons: Strategic (De)Construction of Dynamic Models

关于天使与恶魔：动态模型的战略（破坏）构建

Davide Catta, Rustam Galimullin, Munyque Mittelmann

专题命中 逻辑推理 ：reasoning(abstract)；planning(abstract)

AI总结 本文提出三种逻辑用于研究动态图拓扑中策略的构建与破坏，探讨了其表达能力和模型检查复杂性。

Comments This is an extended version of the paper with the same title that will appear in the proceedings of AAMAS 2026. This version contains a technical appendix with proof details

EgoLog: Ego-Centric Fine-Grained Daily Log with Ubiquitous Wearables

EgoLog：基于普及式可穿戴设备的以自我为中心的细粒度日常日志

Lixing He, Bufang Yang, Di Duan, Zhenyu Yan, Guoliang Xing

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

AI总结 EgoLog通过融合音频与IMU数据及LLM推理，实现了基于普及式可穿戴设备的细粒度日常日志识别，提升了场景和活动识别的准确性。

AgentVNE: LLM-Augmented Graph Reinforcement Learning for Affinity-Aware Multi-Agent Placement in Edge Agentic AI

AgentVNE: 基于大语言模型的图强化学习用于面向亲和力的多智能体部署

Runze Zheng, Yuqing Zheng, Zhengyi Cheng, Long Luo, Haoxiang Luo, Gang Sun, Hongfang Yu, Dusit Niyato

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

AI总结 AgentVNE通过结合大语言模型与图强化学习，解决边缘智能体部署中的动态资源分配与亲和力约束问题，提升服务效率与响应速度。

Large Language Model-Driven Closed-Loop UAV Operation with Semantic Observations

基于大语言模型的闭环无人机操作与语义观测

Wenhao Wang, Yanyan Li, Long Jiao, Jiawei Yuan

机构 * Department of CIS, University of Massachusetts Dartmouth（CIS系，马萨诸塞大学达特茅斯分校） ； Department of CSIS, California State University San Marcos（CSIS系，加州州立大学桑马科斯分校） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

AI总结 本文提出基于大语言模型的闭环无人机操作框架，通过代码生成器和评估器实现可靠操作，提升复杂任务的成功率和完整性。

Comments 13 pages, 10 figures

Bridging Your Imagination with Audio-Video Generation via a Unified Director

通过统一导演模型实现想象力与音频视频生成的连接

Jiaxu Zhang, Tianshu Hu, Yuan Zhang, Zenan Li, Linjie Luo, Guosheng Lin, Xin Chen

机构 * Nanyang Technological University（南洋理工大学） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

AI总结 UniMAGE通过统一导演模型整合脚本起草与关键帧生成，提升非专业人士制作多镜头电影的能力。

More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models

不止于最终答案：提升视觉提取和逻辑一致性的视觉语言模型

Hoang Anh Just, Yifei Fan, Handong Zhao, Jiuxiang Gu, Ruiyi Zhang, Simon Jenni, Kushal Kafle, Ruoxi Jia, Jing Shi

机构 * Virginia Tech（弗吉尼亚理工大学） ； Adobe Research（Adobe研究院） ； Apple（苹果公司） 纠错

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

AI总结 PeRL-VL通过解耦框架提升视觉语言模型的视觉提取和推理一致性，实现Pass@1准确率提升。

Architecting Large Action Models for Human-in-the-Loop Intelligent Robots

为具有人类在环的智能机器人构建大型动作模型

Kanisorn Sangchai, Methasit Boonpun, Withawin Kraipetchara, Paulo Garcia

专题命中 逻辑推理 ：reasoning(abstract)；planning(abstract)

AI总结 本文提出通过整合符号方法与现成模型构建可验证的神经符号智能机器人动作模型，以提升可靠性和可解释性。

CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model

CoC-VLA: 深入研究对抗域转移以实现可解释的自动驾驶 via 链式因果视觉语言动作模型

Dapeng Zhang, Fei Shen, Rui Zhao, Yinda Chen, Peng Zhi, Chenyang Li, Rui Zhou, Qingguo Zhou

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

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

AI总结 CoC-VLA通过链式因果视觉语言动作模型实现对抗域转移，提升自动驾驶的可解释性和长尾场景处理能力。

Examining Student and AI Generated Personalized Analogies in Introductory Physics

Amogh Sirnoorkar, Winter Allen, Syed Furqan Abbas Hashmi, N. Sanjay Rebello

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving

Luke Rowe, Rodrigue de Schaetzen, Roger Girgis, Christopher Pal, Liam Paull

机构 * Mila - Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） ； Polytechnique Montréal（蒙特利尔理工学院） ； CIFAR AI Chair（CIFAR人工智能主席） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

U2F: Encouraging SWE-Agent to Seize Novelty without Losing Feasibility

Wencheng Ye, Yan Liu

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Investigating the Experience of Autistic Individuals in Software Engineering

Madalena Sasportes, Grischa Liebel, Miguel Goulão

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Non-Markovian Discrete Diffusion with Causal Language Models

Yangtian Zhang, Sizhuang He, Daniel Levine, Lawrence Zhao, David Zhang, Syed A Rizvi, Shiyang Zhang, Emanuele Zappala, Rex Ying, David van Dijk

机构 * Yale University（耶鲁大学） 纠错

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

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

A Mimamsa Inspired Framework For Instruction Sequencing In AI Agents

Bama Srinivasan

专题命中 逻辑推理 ：reasoning(abstract)；planning(abstract)

Comments 16 pages

DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education

Lingyue Fu, Haowei Yuan, Datong Chen, Xinyi Dai, Qingyao Li, Weinan Zhang, Weiwen Liu, Yong Yu

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

$\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks

Rana Muhammad Shahroz Khan, Zhen Tan, Sukwon Yun, Charles Fleming, Tianlong Chen

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Arizona State University（亚利桑那州立大学） ； Cisco（思科） 纠错

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

Multi-Hop Question Answering: When Can Humans Help, and Where do They Struggle?

Jinyan Su, Claire Cardie, Jennifer Healey

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models

Yu Yan, Siqi Lu, Yang Gao, Zhaoxuan Li, Ziming Zhao, Qingjun Yuan, Yongjuan Wang

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Comments 19 pages

Query, Don't Train: Privacy-Preserving Tabular Prediction from EHR Data via SQL Queries

Josefa Lia Stoisser, Marc Boubnovski Martell, Kaspar Märtens, Lawrence Phillips, Stephen Michael Town, Rory Donovan-Maiye, Julien Fauqueur

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

Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint

Heekyung Lee, Jiaxin Ge, Tsung-Han Wu, Minwoo Kang, Trevor Darrell, David M. Chan

机构 * POSTECH ； University of California, Berkeley（加州大学伯克利分校） 纠错

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

Comments EMNLP 2025 Main Conference

Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts

Barbara Gendron, Gaël Guibon, Mathieu D'aquin

机构 * Loria, CNRS, Université de Lorraine, Nancy, France（Loria研究所、法国国家科学研究中心、洛林大学、南希分校） ； Université Sorbonne Paris Nord, CNRS, Laboratoire d'Informatique de Paris Nord, LIPN, F-93430 Villetaneuse, France（巴黎北大学、法国国家科学研究中心、巴黎北信息技术实验室、LIPN、法国） 纠错

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

Comments Accepted at TOTh 2025 (Terminology \& Ontology: Theories and applications)

Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework

Qihui Fan, Wenbo Li, Enfu Nan, Yixiao Chen, Lei Lu, Pu Zhao, Yanzhi Wang

机构 * Northeastern University（东北大学） 纠错

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

Frontend Diffusion: Empowering Self-Representation of Junior Researchers and Designers Through Multi-agent System

Zijian Ding, Qinshi Zhang, Mohan Chi, Ziyi Wang

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Extracting Visual Plans from Unlabeled Videos via Symbolic Guidance

Wenyan Yang, Ahmet Tikna, Yi Zhao, Yuying Zhang, Luigi Palopoli, Marco Roveri, Joni Pajarinen

机构 * Department of Electrical Engineering and Automation, Aalto University（艾尔沃斯大学电气工程与自动化系） ； Department of Engineering and Computer Science, University of Trento（特伦托大学工程与计算机科学系） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；planning(abstract)

MoKA: Mixture of Kronecker Adapters

Mohammadreza Sadeghi, Mahsa Ghazvini Nejad, MirHamed Jafarzadeh Asl, Yu Gu, Yuanhao Yu, Masoud Asgharian, Vahid Partovi Nia

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

Augmenting Von Neumann's Architecture for an Intelligent Future

Rajpreet Singh, Vidhi Kothari

专题命中 逻辑推理 ：reasoning(abstract)；planning(abstract)

Comments 6 pages, 2 figures

Strategic Integration of AI Chatbots in Physics Teacher Preparation: A TPACK-SWOT Analysis of Pedagogical, Epistemic, and Cybersecurity Dimensions

N. Mohammadipour

专题命中 逻辑推理 ：reasoning(abstract)；planning(abstract)

Comments 34 pages, 3 figures, 4 tables

A Large Language Model for Chemistry and Retrosynthesis Predictions

Yueqing Zhang, Wentao Liu, Yan Zhang, Danyang Xiong, Jihang Zhai, Hao Hao, YuCheng Gu, HaiBo Yang, Shuanhu Gao, Lianrui Hu, Aimin Zhou, Xiao He

专题命中 逻辑推理 ：reasoning(abstract)；planning(abstract)

Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle

Loïs Vanhée, Melania Borit, Peer-Olaf Siebers, Roger Cremades, Christopher Frantz, Önder Gürcan, František Kalvas, Denisa Reshef Kera, Vivek Nallur, Kavin Narasimhan, Martin Neumann

专题命中 逻辑推理 ：reasoning(abstract)；logical reasoning(abstract)

Comments 18 pages, including 2 pages of appendix, accepted for publication at the Social Simulation Conference 2025 (https://ssc2025.tbm.tudelft.nl/)