大模型推理能力

Do Vision-Language Models Really Understand Visual Language?

Yifan Hou, Buse Giledereli, Yilei Tu, Mrinmaya Sachan

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

Comments ICML 2025

Route Sparse Autoencoder to Interpret Large Language Models

Wei Shi, Sihang Li, Tao Liang, Mingyang Wan, Guojun Ma, Xiang Wang, Xiangnan He

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

Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language

Naiqi Li, Peiyuan Liu, Zheng Liu, Tao Dai, Yong Jiang, Shu-Tao Xia

机构 * Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院） ； Shenzhen University（深圳大学） 纠错

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

MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering

Zhang Siyue, Xue Yuxiang, Zhang Yiming, Wu Xiaobao, Luu Anh Tuan, Zhao Chen

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

A Logic of General Attention Using Edge-Conditioned Event Models (Extended Version)

Gaia Belardinelli, Thomas Bolander, Sebastian Watzl

机构 * Stanford University（斯坦福大学） ； Technical University of Denmark（丹麦技术大学） ； University of Oslo（奥斯陆大学） 纠错

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

ViMo: A Generative Visual GUI World Model for App Agents

Dezhao Luo, Bohan Tang, Kang Li, Georgios Papoudakis, Jifei Song, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao

机构 * Queen Mary University of London（伦敦女王学院） ； University of Oxford（牛津大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； University College London（伦敦大学学院） 纠错

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

Comments https://ai-agents-2030.github.io/ViMo/

DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

Ziyang Zheng, Shan Huang, Jianyuan Zhong, Zhengyuan Shi, Guohao Dai, Ningyi Xu, Qiang Xu

机构 * The Chinese University of Hong Kong（香港中文大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System

Sonu Kumar, Anubhav Girdhar, Ritesh Patil, Divyansh Tripathi

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

Codifying Character Logic in Role-Playing

Letian Peng, Jingbo Shang

机构 * Department of Computer Science University of California, San Diego（计算机科学系加州大学圣地亚哥分校） 纠错

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

Injecting Knowledge Graphs into Large Language Models

Erica Coppolillo

机构 * University of Calabria（卡拉布里亚大学） ； ICAR-CNR（ICAR-国家研究理事会） 纠错

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

RedTeamLLM: an Agentic AI framework for offensive security

Brian Challita, Pierre Parrend

机构 * Laboratoire de Recherche de l’EPITA（EPITA研究实验室） ； ICube, UMR 7357（ICube研究中心） ； Université de Strasbourg（斯特拉斯堡大学） ； CNRS（国家科学研究中心） 纠错

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

RuleGenie: SIEM Detection Rule Set Optimization

Akansha Shukla, Parth Atulbhai Gandhi, Yuval Elovici, Asaf Shabtai

机构 * Beg-Gurion University of the Negev（贝格-加利尔内盖夫大学） 纠错

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

ROSA: A Knowledge-based Solution for Robot Self-Adaptation

Gustavo Rezende Silva, Juliane Päßler, S. Lizeth Tapia Tarifa, Einar Broch Johnsen, Carlos Hernández Corbato

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

Journal ref Front. Robot. AI Sec. Computational Intelligence in Robotics 2025

Geo-Llama: Leveraging LLMs for Human Mobility Trajectory Generation with Spatiotemporal Constraints

Siyu Li, Toan Tran, Haowen Lin, John Krumm, Cyrus Shahabi, Lingyi Zhao, Khurram Shafique, Li Xiong

机构 * Dept. of Computer Science, Emory University（埃默里大学计算机科学系） ； Dept. of Computer Science, University of Southern California（南加州大学计算机科学系） ； Novateur Research Solutions（Novateur研究解决方案） 纠错

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

MAGI: Multi-Agent Guided Interview for Psychiatric Assessment

Guanqun Bi, Zhuang Chen, Zhoufu Liu, Hongkai Wang, Xiyao Xiao, Yuqiang Xie, Wen Zhang, Yongkang Huang, Yuxuan Chen, Libiao Peng, Yi Feng, Minlie Huang

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

Comments In progress

Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models

Nicolas Baumann, Cheng Hu, Paviththiren Sivasothilingam, Haotong Qin, Lei Xie, Michele Magno, Luca Benini

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

Mutual Understanding between People and Systems via Neurosymbolic AI and Knowledge Graphs

Irene Celino, Mario Scrocca, Agnese Chiatti

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

Comments 26 pages, 13 figures, 1 table; pre-print version of book chapter

Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution

Zen Kit Heng, Zimeng Zhao, Tianhao Wu, Yuanfei Wang, Mingdong Wu, Yangang Wang, Hao Dong

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

Comments 7 pages, 5 figures

Neuro-Symbolic AI in 2024: A Systematic Review

Brandon C. Colelough, William Regli

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

Comments 19 pages

Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for education

Danial Hooshyar, Roger Azevedo, Yeongwook Yang

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

Cultivating Game Sense for Yourself: Making VLMs Gaming Experts

Wenxuan Lu, Jiangyang He, Zhanqiu Zhang, Yiwen Guo, Tianning Zang

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

Understanding the Logic of Direct Preference Alignment through Logic

Kyle Richardson, Vivek Srikumar, Ashish Sabharwal

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

The Art of Tool Interface Design

Yunnan Wu, Paul Chen, Deshank Baranwal, Jinlong Zhou, Jian Yuan

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

J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain

Yiran Hu, Huanghai Liu, Qingjing Chen, Ning Zheng, Chong Wang, Yun Liu, Charles L. A. Clarke, Weixing Shen

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

Comments 10 pages, 5 figures

Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models

Han Cao, Lingwei Wei, Wei Zhou, Songlin Hu

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

Comments Accepted by AAAI 2025

Benchmarking Chinese Medical LLMs: A Medbench-based Analysis of Performance Gaps and Hierarchical Optimization Strategies

Luyi Jiang, Jiayuan Chen, Lu Lu, Xinwei Peng, Lihao Liu, Junjun He, Jie Xu

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

Performant LLM Agentic Framework for Conversational AI

Alex Casella, Wayne Wang

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

Comments 6 pages, 3 figures

Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation

Pierrick Lorang, Hong Lu, Matthias Scheutz

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

Comments 8 pages, 4 figures. Accepted at ICRA 2025

Extracting Symbolic Sequences from Visual Representations via Self-Supervised Learning

Victor Sebastian Martinez Pozos, Ivan Vladimir Meza Ruiz

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

Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuning

Wenshuai Huo, Xiaocheng Feng, Yichong Huang, Chengpeng Fu, Baohang Li, Yangfan Ye, Zhirui Zhang, Dandan Tu, Duyu Tang, Yunfei Lu, Hui Wang, Bing Qin

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

Comments Accepted at AAAI 2025