大模型推理能力

Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs

Yanwei Ren, Liu Liu, Baosheng Yu, Jiayan Qiu, Quan Chen

机构 * School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院） ； Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院） ； Nanyang Technological University（南洋理工大学） ； University of Leicester（莱斯特大学） ； Kuaishou Technology（快手科技） 纠错

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

Integrating LLMs and Digital Twins for Adaptive Multi-Robot Task Allocation in Construction

Min Deng, Bo Fu, Lingyao Li, Xi Wang

机构 * Department of Civil, Environmental, and Construction Engineering, Texas Tech University（土木、环境与建设工程系，德克萨斯科技大学） ； Amazon Robotics（亚马逊机器人技术） ； School of Information, University of South Florida（信息学院，佛罗里达州立大学） ； Department of Construction Science, Texas A&M University（建设科学系，德克萨斯农工大学） 纠错

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

Large Language Models for Spreadsheets: Benchmarking Progress and Evaluating Performance with FLARE

Simon Thorne

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

Comments 18 Pages, 10 Tables, 1 Colour Figure

Journal ref Proceedings of the EuSpRIG 2025 Conference "Spreadsheet Risk Management", University of Greenwich, London, ISBN: 978-1-905404-60-5

Minimizing False Positives in Static Bug Detection via LLM-Enhanced Path Feasibility Analysis

Xueying Du, Kai Yu, Chong Wang, Yi Zou, Wentai Deng, Zuoyu Ou, Xin Peng, Lingming Zhang, Yiling Lou

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

From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies

Blaž Škrlj, Boshko Koloski, Senja Pollak, Nada Lavrač

机构 * Jožef Stefan Institute（乔泽夫·斯塔芬研究所） 纠错

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

Comments To-appear as a book chapter

RE-oriented Model Development with LLM Support and Deduction-based Verification

Radoslaw Klimek

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

Comments The paper has been peer-reviewed and accepted for publication to the 1st International Workshop on Artificial Intelligence for Integrated Development Environments (AI-IDE) of the 33rd ACM Symposium on the Foundations of Software Engineering (FSE '25), June 23--27, 2025, Trondheim, Norway

A Framework Leveraging Large Language Models for Autonomous UAV Control in Flying Networks

Diana Nunes, Ricardo Amorim, Pedro Ribeiro, André Coelho, Rui Campos

机构 * INESC TEC and Faculdade de Engenharia, Universidade do Porto（INESC TEC和工程学院，葡萄牙波尔图大学） 纠错

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

Comments 6 pages, 3 figures, 6 tables

Can Large Language Models Understand Intermediate Representations in Compilers?

Hailong Jiang, Jianfeng Zhu, Yao Wan, Bo Fang, Hongyu Zhang, Ruoming Jin, Qiang Guan

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

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

Ke Niu, Haiyang Yu, Mengyang Zhao, Teng Fu, Siyang Yi, Wei Lu, Bin Li, Xuelin Qian, Xiangyang Xue

机构 * Fudan University（复旦大学） ； Northwestern Polytechnical University（西北工业大学） 纠错

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

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

Yongchao Chen, Yilun Hao, Yueying Liu, Yang Zhang, Chuchu Fan

机构 * Massachusetts Institute of Technology, Boston, MA, USA（麻省理工学院） ； Harvard University, Boston, MA, USA（哈佛大学） ； MIT-IBM Watson AI Lab, Boston, MA, USA（MIT-IBM Watson AI实验室） ； University of Illinois Urbana-Champaign, Urbana, IL, USA（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments 28 pages, 12 figures

Journal ref International Conference on Machine Learning (ICML'2025)

Can Large Language Models Understand Symbolic Graphics Programs?

Zeju Qiu, Weiyang Liu, Haiwen Feng, Zhen Liu, Tim Z. Xiao, Katherine M. Collins, Joshua B. Tenenbaum, Adrian Weller, Michael J. Black, Bernhard Schölkopf

机构 * Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所） ； University of Cambridge（剑桥大学） ； MIT（麻省理工学院） 纠错

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

Comments ICLR 2025 Spotlight (v4: 47 pages, 26 figures, project page: https://sgp-bench.github.io/)

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Zhihe Yang, Xufang Luo, Zilong Wang, Dongqi Han, Zhiyuan He, Dongsheng Li, Yunjian Xu

机构 * The Chinese University of Hong Kong（香港中文大学） ； Microsoft Research Asia（微软亚洲研究院） 纠错

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

Comments 24 pages, 12 figures

VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments

Daeun Song, Jing Liang, Xuesu Xiao, Dinesh Manocha

机构 * Department of Computer Science, George Mason University（乔治·马歇尔大学计算机科学系） ； Department of Computer Science, University of Maryland（马里兰大学计算机科学系） 纠错

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

Neuro-Symbolic Concepts

Jiayuan Mao, Joshua B. Tenenbaum, Jiajun Wu

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Stanford University（斯坦福大学） 纠错

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

Comments To appear in Communications of the ACM

Large Language Model Agent as a Mechanical Designer

Yayati Jadhav, Amir Barati Farimani

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

MCP-Solver: Integrating Language Models with Constraint Programming Systems

Stefan Szeider

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

Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction

Zongzheng Zhang, Xinrun Li, Sizhe Zou, Guoxuan Chi, Siqi Li, Xuchong Qiu, Guoliang Wang, Guantian Zheng, Leichen Wang, Hang Zhao, Hao Zhao

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

Comments ICRA 2025, Project Page: https://github.com/XR-Lee/neural-symbolic

Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection

Abhinav Lalwani, Tasha Kim, Lovish Chopra, Christopher Hahn, Zhijing Jin, Mrinmaya Sachan

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

Points2Plans: From Point Clouds to Long-Horizon Plans with Composable Relational Dynamics

Yixuan Huang, Christopher Agia, Jimmy Wu, Tucker Hermans, Jeannette Bohg

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

Comments Project page: https://sites.google.com/stanford.edu/points2plans. 23 pages, 11 figures. Accepted to the IEEE International Conference on Robotics and Automation (ICRA) 2025

Pre-trained Vision-Language Models Learn Discoverable Visual Concepts

Yuan Zang, Tian Yun, Hao Tan, Trung Bui, Chen Sun

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

Comments Transactions on Machine Learning Research, 2025

HaVen: Hallucination-Mitigated LLM for Verilog Code Generation Aligned with HDL Engineers

Yiyao Yang, Fu Teng, Pengju Liu, Mengnan Qi, Chenyang Lv, Ji Li, Xuhong Zhang, Zhezhi He

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

Baichuan4-Finance Technical Report

Hanyu Zhang, Boyu Qiu, Yuhao Feng, Shuqi Li, Qian Ma, Xiyuan Zhang, Qiang Ju, Dong Yan, Jian Xie

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

Out-of-distribution generalization via composition: a lens through induction heads in Transformers

Jiajun Song, Zhuoyan Xu, Yiqiao Zhong

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

Comments 46 pages, 27 figures

LLM-Aided Efficient Hardware Design Automation

Kangwei Xu, Ruidi Qiu, Zhuorui Zhao, Grace Li Zhang, Ulf Schlichtmann, Bing Li

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

Composite Learning Units: Generalized Learning Beyond Parameter Updates to Transform LLMs into Adaptive Reasoners

Santosh Kumar Radha, Oktay Goktas

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

Logically Consistent Language Models via Neuro-Symbolic Integration

Diego Calanzone, Stefano Teso, Antonio Vergari

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

Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving

Yunsheng Ma, Amr Abdelraouf, Rohit Gupta, Ziran Wang, Kyungtae Han

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

Comments 10 pages, 3 figures, 4 tables

Hypergraph Multi-modal Large Language Model: Exploiting EEG and Eye-tracking Modalities to Evaluate Heterogeneous Responses for Video Understanding

Minghui Wu, Chenxu Zhao, Anyang Su, Donglin Di, Tianyu Fu, Da An, Min He, Ya Gao, Meng Ma, Kun Yan, Ping Wang

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

Comments Accepted by ACM MULTIMEDIA 2024

Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models

Ningke Li, Yuekang Li, Yi Liu, Ling Shi, Kailong Wang, Haoyu Wang

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

Comments 29 pages, 11 figures, 4 tables, to appear in OOPSLA'24 (Vol.8, No.OOPSLA2, Article 336)

RoadPainter: Points Are Ideal Navigators for Topology transformER

Zhongxing Ma, Shuang Liang, Yongkun Wen, Weixin Lu, Guowei Wan

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

Comments 17 pages, 5 figures, Accepted by ECCV 2024