大模型推理能力

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning

DiJia Su, Hanlin Zhu, Yingchen Xu, Jiantao Jiao, Yuandong Tian, Qinqing Zheng

机构 * Meta AI 纠错

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

Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic

Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Bernard Ghanem

专题命中 数学推理 ：reasoning(title,abstract)；chain-of-thought(title)；分类 cs.CL

Comments Under Review

Throttling Web Agents Using Reasoning Gates

Abhinav Kumar, Jaechul Roh, Ali Naseh, Amir Houmansadr, Eugene Bagdasarian

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） 纠错

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

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning

Ang Li, Zhihang Yuan, Yang Zhang, Shouda Liu, Yisen Wang

机构 * PKU（北京大学） ； ByteDance Seed（字节跳动种子） 纠错

专题命中 数学推理 ：reasoning(abstract)；test-time compute(abstract)；分类 cs.AI

LLMs cannot spot math errors, even when allowed to peek into the solution

KV Aditya Srivatsa, Kaushal Kumar Maurya, Ekaterina Kochmar

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫莫德·宾·扎耶德人工智能大学） 纠错

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

Comments Accepted to EMNLP 2025

Hermes 4 Technical Report

Ryan Teknium, Roger Jin, Jai Suphavadeeprasit, Dakota Mahan, Jeffrey Quesnelle, Joe Li, Chen Guang, Shannon Sands, Karan Malhotra

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

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution

Jinzhou Tang, Jusheng Zhang, Qinhan Lv, Sidi Liu, Jing Yang, Chengpei Tang, Keze Wang

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

RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning

Liam Boyle, Nicolas Baumann, Paviththiren Sivasothilingam, Michele Magno, Luca Benini

专题命中 数学推理 ：reasoning(abstract)

An LLM-enabled semantic-centric framework to consume privacy policies

Rui Zhao, Vladyslav Melnychuk, Jun Zhao, Jesse Wright, Nigel Shadbolt

机构 * University of Oxford（牛津大学） 纠错

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

The Application of Virtual Environments and Artificial Intelligence in Higher Education: Experimental Findings in Philosophy Teaching

Adel Vehrer, Zsolt Palfalusi

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

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors

Hao Yang, Zhiyu Yang, Yunjie Zhang, Shanyi Zhu, Lin Yang

机构 * School of Intelligence Science and Technology, National Key Laboratory for Novel Software Technology, Nanjing University（智能科学与技术学院，新型软件技术国家重点实验室，南京大学） ； School of Computing and Information Systems, Singapore Management University（计算与信息系统学院，新加坡管理大学） ； Central South University（中南大学） ； School of Global Education and Development, International Chinese Language Education, University of Chinese Academy of Social Sciences（全球教育与发展学院，国际中文教育，中国社会科学院） 纠错

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

Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval

Yuxiang Liu, Tian Wang, Gourab Kundu, Tianyu Cao, Guang Cheng, Zhen Ge, Jianshu Chen, Qingjun Cui, Trishul Chilimbi

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Amazon（亚马逊） 纠错

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

Comments CIKM 2025

Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation

Andrew G. A. Correa, Ana C. H de Matos

机构 * Monostate（莫诺态） 纠错

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

Comments 9 pages, 2 figures, 4 tables

Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation

Kevin Alcedo, Pedro U. Lima, Rachid Alami

机构 * Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa（系统机器人研究所，理工学院，里斯本大学） ； LAAS-CNRS, Artificial and Natural Intelligence Toulouse Institute (ANITI)（LAAS-CNRS，图卢兹人工智能研究所（ANITI）） 纠错

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

Comments Accepted as a regular paper at the 2025 IEEE International Conference on Robot & Human Interactive Communication (RO-MAN). \c{opyright} 2025 IEEE. The final version will appear in IEEE Xplore

Mic Drop or Data Flop? Evaluating the Fitness for Purpose of AI Voice Interviewers for Data Collection within Quantitative & Qualitative Research Contexts

Shreyas Tirumala, Nishant Jain, Danny D. Leybzon, Trent D. Buskirk

机构 * VKL Research, Inc.（VKL研究公司） ； Old Dominion University（旧 Dominion 大学） 纠错

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

Probabilistically stable revision and comparative probability: a representation theorem and applications

Krzysztof Mierzewski

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

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

TRACE-CS: A Hybrid Logic-LLM System for Explainable Course Scheduling

Stylianos Loukas Vasileiou, William Yeoh

机构 * New Mexico State University（新墨西哥州立大学） ； Washington University in St. Louis（圣路易斯华盛顿大学） 纠错

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

Lagrangian Relaxation for Multi-Action Partially Observable Restless Bandits: Heuristic Policies and Indexability

Rahul Meshram, Kesav Kaza

机构 * Department of Electrical Engineering, Indian Institute of Technology Madras（印度理工学院马德拉斯分校电子工程系） ； Department of Electrical Engineering and Computer Science, University of Ottawa（渥太华大学电子工程与计算机科学系） 纠错

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

Comments 13 pages

Graded Transformers

Tony Shaska

机构 * Department of Mathematics ； Statistics, Oakland University, Rochester, MI 48309 纠错

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

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

专题命中 逻辑推理 ：reasoning(abstract)

Intelligent Assistants for the Semiconductor Failure Analysis with LLM-Based Planning Agents

Aline Dobrovsky, Konstantin Schekotihin, Christian Burmer

机构 * University of the Bundeswehr Munich（联邦国防军大学慕尼黑） ； University Klagenfurt（克雷格弗尔特大学） ； Infineon Technologies AG（英飞凌科技） 纠错

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

Comments This technical report provides evaluation details of the experiments presented in the paper accepted to ISTFA 2025

Learning Social Heuristics for Human-Aware Path Planning

Andrea Eirale, Matteo Leonetti, Marcello Chiaberge

机构 * Department of Electronics and Telecommunications (DET) Politecnico di Torino（电子工程与电信学院（DET）理工学院） ； Department of Informatics King’s College London（信息学院伦敦国王学院） 纠错

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

Cooperative Multi-Agent Path Planning for Heterogeneous UAVs in Contested Environments

Grant Stagg, Cameron K. Peterson

专题命中 规划推理 ：planning(title,abstract)

Comments Submitted to AIAA Journal of Guidance, Control, and Dynamics (in review)

Language-Guided Long Horizon Manipulation with LLM-based Planning and Visual Perception

Changshi Zhou, Haichuan Xu, Ningquan Gu, Zhipeng Wang, Bin Cheng, Pengpeng Zhang, Yanchao Dong, Mitsuhiro Hayashibe, Yanmin Zhou, Bin He

专题命中 规划推理 ：planning(title,abstract)

Push-1 is PSPACE-complete, and the automated verification of motion planning gadgets

Zachary DeStefano, Bufang Liang

专题命中 规划推理 ：planning(title,abstract)

Comments Added short addendum on concurrent work and small citation fixes

Domain-Conditioned Scene Graphs for State-Grounded Task Planning

Jonas Herzog, Jiangpin Liu, Yue Wang

机构 * Zhejiang University（浙江大学） 纠错

专题命中 规划推理 ：planning(title,abstract)

Comments Accepted for IROS 2025

Re-evaluating LLM-based Heuristic Search: A Case Study on the 3D Packing Problem

Guorui Quan, Mingfei Sun, Manuel López-Ibáñez

机构 * The University of Manchester（曼彻斯特大学） ； University of Manchester（曼彻斯特大学） ； Department of Computer Science（计算机科学系） ； Alliance Manchester Business School（曼彻斯特商业联盟学院） 纠错

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

Mobile-Agent-v3: Fundamental Agents for GUI Automation

Jiabo Ye, Xi Zhang, Haiyang Xu, Haowei Liu, Junyang Wang, Zhaoqing Zhu, Ziwei Zheng, Feiyu Gao, Junjie Cao, Zhengxi Lu, Jitong Liao, Qi Zheng, Fei Huang, Jingren Zhou, Ming Yan

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

Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction

Aishni Parab, Hongjing Lu, Ying Nian Wu, Sumit Gulwani

机构 * Department of Statistics, University of California, Los Angeles（统计学系，加州大学洛杉矶分校） ； Microsoft, Redmond, WA（微软公司，西雅图，华盛顿州） ； Department of Psychology, University of California, Los Angeles（心理学系，加州大学洛杉矶分校） 纠错

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

Comments This is the preprint version corresponding to our NeurIPS 2025 Workshop on Multimodal Algorithmic Reasoning submission

Cloud-Device Collaborative Agents for Sequential Recommendation

Jing Long, Sirui Huang, Huan Huo, Tong Chen, Hongzhi Yin, Guandong Xu

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)