大模型推理能力

Self-Questioning Language Models

Lili Chen, Mihir Prabhudesai, Katerina Fragkiadaki, Hao Liu, Deepak Pathak

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

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

HOFT: Householder Orthogonal Fine-tuning

Alejandro Moreno Arcas, Albert Sanchis, Jorge Civera, Alfons Juan

机构 * MLLP group, Valencian Research Institute for Artificial Intelligence（瓦伦西亚人工智能研究 institute 的 MLLP 组） ； Universitat Politècnica de València, Spain（瓦伦西亚理工大学，西班牙） 纠错

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

AdsQA: Towards Advertisement Video Understanding

Xinwei Long, Kai Tian, Peng Xu, Guoli Jia, Jingxuan Li, Sa Yang, Yihua Shao, Kaiyan Zhang, Che Jiang, Hao Xu, Yang Liu, Jiaheng Ma, Bowen Zhou

机构 * Tsinghua University（清华大学） ； Peking University（北京大学） ； CASIA（中国科学院自动化所） ； Harvard University（哈佛大学） ； Shanghai Artificial Intelligence Lab（上海人工智能实验室） 纠错

专题命中 数学推理 ：reasoning(abstract)

Comments ICCV-2025

VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making

Mohamed Salim Aissi, Clemence Grislain, Mohamed Chetouani, Olivier Sigaud, Laure Soulier, Nicolas Thome

机构 * Sorbonne Université, CNRS, ISIR（索邦大学、国家科学研究中心、ISIR） 纠错

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

Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following

Minjong Yoo, Jinwoo Jang, Wei-jin Park, Honguk Woo

机构 * Department of Computer Science and Engineering, Sungkyunkwan University（全南大学计算机科学与工程系） ； Acryl Inc.（阿克罗尔公司） 纠错

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

Comments 21 pages. NeurIPS 2024

Journal ref Advances in Neural Information Processing Systems 37, 67034-67060, 2024

Depth-Bounded Epistemic Planning

Thomas Bolander, Alessandro Burigana, Marco Montali

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

Comments Extended version of paper accepted at KR 2025

Diffusion-Guided Multi-Arm Motion Planning

Viraj Parimi, Brian C. Williams

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

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

TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making

Kechen Jiao, Zhirui Fang, Jiahao Liu, Bei Li, Qifan Wang, Xinyu Liu, Junhao Ruan, Zhongjian Qiao, Yifan Zhu, Yaxin Xu, Jingang Wang, Xiu Li

机构 * Tsinghua University（清华大学） ； Meituan（美团） ； Northeastern University（东北大学） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Meta AI ； Wuhan University（武汉大学） 纠错

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

Prior Prompt Engineering for Reinforcement Fine-Tuning

Pittawat Taveekitworachai, Potsawee Manakul, Sarana Nutanong, Kunat Pipatanakul

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

Comments Accepted at EMNLP 2025, Main; 26 pages, 42 figures

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations

Ron F. Del Rosario, Klaudia Krawiecka, Christian Schroeder de Witt

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

An Iterative LLM Framework for SIBT utilizing RAG-based Adaptive Weight Optimization

Zhuo Xiao, Qinglong Yao, Jingjing Wang, Fugen Zhou, Bo Liu, Haitao Sun, Zhe Ji, Yuliang Jiang, Junjie Wang, Qiuwen Wu

机构 * Image Processing Center, Beihang University（北航图像处理中心） ； Department of Radiation Oncology, Peking University Third Hospital（北京大学第三医院放射肿瘤科） ； Department of Radiation Oncology, Duke University Medical Center（杜克大学医学中心放射肿瘤科） 纠错

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

MPO: Boosting LLM Agents with Meta Plan Optimization

Weimin Xiong, Yifan Song, Qingxiu Dong, Bingchan Zhao, Feifan Song, Xun Wang, Sujian Li

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

Comments EMNLP 2025 Findings

Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI

Payam Saeedi, Mahsa Goodarzi, M Abdullah Canbaz

机构 * Golisano Institute for Sustainability Rochester Institute of Technology Rochester, The United States ； Information Sciences \& Technology, CEHC University at Albany, SUNY Albany, The United States 纠错

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

Narrative-Guided Reinforcement Learning: A Platform for Studying Language Model Influence on Decision Making

Anup Tuladhar, Araz Minhas, Adam Kirton, Eli Kinney-Lang

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

Comments Extended Abstract for RLDM 2025

One Model, Two Minds: A Context-Gated Graph Learner that Recreates Human Biases

Shalima Binta Manir, Tim Oates

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

Comments 9 pages, 7 figures, 2 tables

Multimodal Medical Disease Classification with LLaMA II

Christian Gapp, Elias Tappeiner, Martin Welk, Rainer Schubert

机构 * Institute of Biomedical Image Analysis UMIT TIROL（生物医学影像分析研究所 UMIT TIROL） ； UMIT TIROL – Private University for Health Sciences and Health Technology（UMIT TIROL – 健康科学与健康技术私立大学） ； VASCage – Centre on Clinical Stroke Research Innsbruck（VASCage – 神经科学临床研究中心 Innsbruck） 纠错

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

Comments 9 pages, 6 figures, conference: AIRoV -- The First Austrian Symposium on AI, Robotics, and Vision 25.-27.3.2024, Innsbruck

Dual-Stage Safe Herding Framework for Adversarial Attacker in Dynamic Environment

Wenqing Wang, Ye Zhang, Haoyu Li, Jingyu Wang

专题命中 规划推理 ：planning(abstract)

MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning

Chenghao Liu, Zhimu Zhou, Jiachen Zhang, Minghao Zhang, Songfang Huang, Huiling Duan

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

Comments 9 pages, 4 figures

Interpretable Physics Reasoning and Performance Taxonomy in Vision-Language Models

Pranav Pawar, Kavish Shah, Akshat Bhalani, Komal Kasat, Dev Mittal, Hadi Gala, Deepali Patil, Nikita Raichada, Monali Deshmukh

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

SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation

Michael J. Munje, Chen Tang, Shuijing Liu, Zichao Hu, Yifeng Zhu, Jiaxun Cui, Garrett Warnell, Joydeep Biswas, Peter Stone

机构 * Department of Computer Science, The University of Texas at Austin（德克萨斯大学计算机科学系） ； Army Research Laboratory（陆军研究实验室） ； Sony AI（索尼人工智能） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Conference on Robot Learning (CoRL) 2025 Project site: https://larg.github.io/socialnav-sub

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy, Ben Fielding, Tristin Forbus, Harry Grieve, Semih Kara, Jari Kolehmainen, Yihua Lou, Christopher Nies, Edward Phillip Flores Nuño, Diogo Ortega, Shikhar Rastogi, Austin Virts, Matthew J. Wright

机构 * Gensyn AI Team（Gensyn AI团队） 纠错

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

Comments 14 pages, 6 figures

CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models

Feiyang Li, Peng Fang, Zhan Shi, Arijit Khan, Fang Wang, Weihao Wang, Xin Zhang, Yongjian Cui

机构 * School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China（华中科技大学计算机科学与技术学院） ； Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, China（华中科技大学光电实验室） ； Department of Computer Science, Bowling Green State University, Ohio, USA（Bowling Green State University 计算机科学系） ； Department of Computer Science, Aalborg University, Aalborg, Denmark（Aalborg University 计算机科学系） ； Huawei Technologies Co., Ltd, Shenzhen, China（华为技术有限公司） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；CoT(title,abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Investigating Compositional Reasoning in Time Series Foundation Models

Willa Potosnak, Cristian Challu, Mononito Goswami, Kin G. Olivares, Michał Wiliński, Nina Żukowska, Artur Dubrawski

机构 * Auton Lab, School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学系自动化实验室） ； Nixtla ； Amazon（亚马逊） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.LG

Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning

Kavi Gupta, Kate Sanders, Armando Solar-Lezama

专题命中 复杂问题求解 ：reasoning(title)；chain-of-thought(abstract)；分类 cs.LG

Comments 10 pages, 4 figures, 2 tables

SciGPT: A Large Language Model for Scientific Literature Understanding and Knowledge Discovery

Fengyu She, Nan Wang, Hongfei Wu, Ziyi Wan, Jingmian Wang, Chang Wang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Have Large Vision-Language Models Mastered Art History?

Ombretta Strafforello, Derya Soydaner, Michiel Willems, Anne-Sofie Maerten, Stefanie De Winter

机构 * KU Leuven（库勒韦恩大学） ； Leiden University（莱顿大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

How Far Are We from Optimal Reasoning Efficiency?

Jiaxuan Gao, Shu Yan, Qixin Tan, Lu Yang, Shusheng Xu, Wei Fu, Zhiyu Mei, Kaifeng Lyu, Yi Wu

机构 * IIIS, Tsinghua University（清华大学信息学院） ； Ant Research, RL Lab（蚂蚁研究院强化学习实验室） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model

Yanlong Wang, Jian Xu, Fei Ma, Hongkang Zhang, Hang Yu, Tiantian Gao, Yu Wang, Haochen You, Shao-Lun Huang, Danny Dongning Sun, Xiao-Ping Zhang

机构 * Tsinghua University（清华大学） ； Pengcheng Laboratory（鹏城实验室） ； Guangming Laboratory（光明实验室） ； Ant Group（蚂蚁集团） ； Columbia University（哥伦比亚大学） ； Southern University of Science and Technology（南方科技大学） 纠错

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

Scaling Truth: The Confidence Paradox in AI Fact-Checking

Ihsan A. Qazi, Zohaib Khan, Abdullah Ghani, Agha A. Raza, Zafar A. Qazi, Wassay Sajjad, Ayesha Ali, Asher Javaid, Muhammad Abdullah Sohail, Abdul H. Azeemi

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

Comments 65 pages, 26 figures, 6 tables

A New Dataset and Benchmark for Grounding Multimodal Misinformation

Bingjian Yang, Danni Xu, Kaipeng Niu, Wenxuan Liu, Zheng Wang, Mohan Kankanhalli

机构 * National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University（多媒体软件国家工程研究中心，计算机科学学院，武汉大学） ； School of Computing, National University of Singapore（计算学院，新加坡国立大学） ； School of Computer Science, Peking University（计算机科学学院，北京大学） ； State Key Laboratory for Multimedia Information Processing, Peking University（多媒体信息处理国家重点实验室，北京大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

Comments 6 pages, 5 figures, ACM Multimedia 2025 Dataset Track