大模型推理能力

MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications

Vishnou Vinayagame, Gregory Senay, Luis Martí

机构 * Docugami Inc（Docugami公司） ； University of Toronto（多伦多大学） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments Published as a conference paper at ICDAR 2025

Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset

Rabeeh Karimi Mahabadi, Sanjeev Satheesh, Shrimai Prabhumoye, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro

机构 * NVIDIA（英伟达） ； Boston University（波士顿大学） 纠错

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

Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding

Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Zhejiang University（浙江大学） ； Princeton University（普林斯顿大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments ICML 2025

Dream 7B: Diffusion Large Language Models

Jiacheng Ye, Zhihui Xie, Lin Zheng, Jiahui Gao, Zirui Wu, Xin Jiang, Zhenguo Li, Lingpeng Kong

机构 * The University of Hong Kong（香港大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 数学推理 ：planning(abstract)；分类 cs.CL

AI Testing Should Account for Sophisticated Strategic Behaviour

Vojtech Kovarik, Eric Olav Chen, Sami Petersen, Alexis Ghersengorin, Vincent Conitzer

机构 * Department of Computer Science（计算机科学系） ； Czech Technical University Prague（捷克技术大学布拉格） ； Global Priorities Institute（全球优先研究所） ； University of Oxford（牛津大学） ； Foundations of Cooperative AI Lab（合作人工智能基础实验室） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 代码与定理证明 ：reasoning(abstract)；分类 cs.AI

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning

Yekun Zhu, Guang Chen, Chengjun Mao

专题命中 逻辑推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；logical reasoning(abstract)；分类 cs.AI、cs.LG

A Fully Spectral Neuro-Symbolic Reasoning Architecture with Graph Signal Processing as the Computational Backbone

Andrew Kiruluta

机构 * Andrew Kiruluta（独立研究者） 纠错

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

Discovering Hidden Algebraic Structures via Transformers with Rank-Aware Beam GRPO

Jaeha Lee, Gio Huh, Ning Su, Tony Yue YU

机构 * California Institute of Technology（加州理工学院） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

R-ConstraintBench: Evaluating LLMs on NP-Complete Scheduling

Raj Jain, Marc Wetter

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

QueryGenie: Making LLM-Based Database Querying Transparent and Controllable

Longfei Chen, Shenghan Gao, Shiwei Wang, Ken Lin, Yun Wang, Quan Li

专题命中 逻辑推理 ：reasoning(abstract)

Comments Accepted by The 38th Annual ACM Symposium on User Interface Software and Technology (UIST Adjunct '25), September 28-October 1, 2025, Busan, Republic of Korea

In-Context Iterative Policy Improvement for Dynamic Manipulation

Mark Van der Merwe, Devesh Jha

机构 * Department of Robotics, University of Michigan（机器人学系，密歇根大学） ； MERL 纠错

专题命中 逻辑推理 ：reasoning(abstract)

Comments 14 pages. Accepted at CoRL 2025

LLM-Driven Self-Refinement for Embodied Drone Task Planning

Deyu Zhang, Xicheng Zhang, Jiahao Li, Tingting Long, Xunhua Dai, Yongjian Fu, Jinrui Zhang, Ju Ren, Yaoxue Zhang

机构 * School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院） ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） 纠错

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

Comments 14pages

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration

Romain Lacombe, Kerrie Wu, Eddie Dilworth

机构 * Stanford University（斯坦福大学） 纠错

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

Comments Published at ICML 2025 Workshop on Reliable and Responsible Foundation Models

Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation

Nikita Kachaev, Andrei Spiridonov, Andrey Gorodetsky, Kirill Muravyev, Nikita Oskolkov, Aditya Narendra, Vlad Shakhuro, Dmitry Makarov, Aleksandr I. Panov, Polina Fedotova, Alexey K. Kovalev

机构 * AIRI ； Moscow Institute of Physics and Technology (MIPT)（莫斯科物理技术学院） ； Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学） ； Sberbank, Robotics Center（Sberbank机器人中心） ； Skoltech 纠错

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

RETAIL: Towards Real-world Travel Planning for Large Language Models

Bin Deng, Yizhe Feng, Zeming Liu, Qing Wei, Xiangrong Zhu, Shuai Chen, Yuanfang Guo, Yunhong Wang

机构 * School of Computer Science and Engineering, Beihang University, Beijing, China（北京航空航天大学计算机科学与工程学院） ； Meituan Inc., China（美团公司） 纠错

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

Embodied Long Horizon Manipulation with Closed-loop Code Generation and Incremental Few-shot Adaptation

Yuan Meng, Xiangtong Yao, Haihui Ye, Yirui Zhou, Shengqiang Zhang, Zhenguo Sun, Xukun Li, Zhenshan Bing, Alois Knoll

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

Comments update ICRA 6 page

Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback

Yuxing Lu, Yucheng Hu, Nan Sun, Xukai Zhao

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

Comments 9 pages, 4 figures, 4 tables

Prescriptive Agents based on RAG for Automated Maintenance (PARAM)

Chitranshu Harbola, Anupam Purwar

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

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents

Hengyu An, Jinghuai Zhang, Tianyu Du, Chunyi Zhou, Qingming Li, Tao Lin, Shouling Ji

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

Comments EMNLP 2025

IBPS: Indian Bail Prediction System

Puspesh Kumar Srivastava, Uddeshya Raj, Praveen Patel, Shubham Kumar Nigam, Noel Shallum, Arnab Bhattacharya

机构 * IIT Kanpur, India（印度克达尔理工大学） ； Symbiosis Law School Pune, India（印度浦那塞布里奥斯法学院） 纠错

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

S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner

Shuang Ao, Gopal Rumchurn

机构 * Shuang Ao ； Gopal Rumchurn 纠错

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

Comments 9 pages, 2 figures

MaskSDM with Shapley values to improve flexibility, robustness, and explainability in species distribution modeling

Robin Zbinden, Nina van Tiel, Gencer Sumbul, Chiara Vanalli, Benjamin Kellenberger, Devis Tuia

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

DeepThink3D: Enhancing Large Language Models with Programmatic Reasoning in Complex 3D Situated Reasoning Tasks

Jiayi Song, Rui Wan, Lipeng Ma, Weidong Yang, Qingyuan Zhou, Yixuan Li, Ben Fei

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

RATopo: Improving Lane Topology Reasoning via Redundancy Assignment

Han Li, Shaofei Huang, Longfei Xu, Yulu Gao, Beipeng Mu, Si Liu

机构 * School of Artificial Intelligence Beihang University Beijing China（人工智能学院 北航 北京 中国） ； Zhongguancun Academy Beijing China（中关村学院 北京 中国） ； Hangzhou International Innovation Institute Beihang University Hangzhou China（杭州国际创新研究院 北航 杭州 中国） ； Beihang University（北航） ； Zhongguancun Academy（中关村学院） ； University of Macau（澳门大学） 纠错

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

Comments Accepted by ACM MM 2025

AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation

Ruipu Wu, Yige Zhang, Jinyu Chen, Linjiang Huang, Shifeng Zhang, Xu Zhou, Liang Wang, Si Liu

机构 * Beihang University（北京航空航天大学） ； Sangfor Technologies Inc.（深信服科技有限公司） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Accepted by ACM MM 2025

VerifiAgent: a Unified Verification Agent in Language Model Reasoning

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

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

Comments EMNLP 2025

Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models

Yuanchen Zhou, Shuo Jiang, Jie Zhu, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang

机构 * School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院） ； Qwen DianJin Team, Alibaba Cloud Computing（阿里云量子金融团队） 纠错

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

Learning to Generate Unit Tests for Automated Debugging

Archiki Prasad, Elias Stengel-Eskin, Justin Chih-Yao Chen, Zaid Khan, Mohit Bansal

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

专题命中 测试时计算 ：test-time compute(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to COLM 2025. Dataset and Code: https://github.com/archiki/UTGenDebug

Deep Think with Confidence

Yichao Fu, Xuewei Wang, Yuandong Tian, Jiawei Zhao

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

SAND: Boosting LLM Agents with Self-Taught Action Deliberation

Yu Xia, Yiran Shen, Junda Wu, Tong Yu, Sungchul Kim, Ryan A. Rossi, Lina Yao, Julian McAuley

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

Comments EMNLP 2025