大模型推理能力

EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos

Junyi Ma, Erhang Zhang, Yin-Dong Zheng, Yuchen Xie, Yixuan Zhou, Hesheng Wang

机构 * IRMV Lab, the Department of Automation, Shanghai Jiao Tong University（IRMV实验室，自动化系，上海交通大学） 纠错

专题命中 规划推理 ：planning(abstract)

Comments Extended journal version of arXiv:2506.03662

Simple o3: Towards Interleaved Vision-Language Reasoning

Ye Wang, Qianglong Chen, Zejun Li, Siyuan Wang, Shijie Guo, Zhirui Zhang, Zhongyu Wei

机构 * Independent Researcher（独立研究者） 纠错

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

Exploring Multimodal AI Reasoning for Meteorological Forecasting from Skew-T Diagrams

ChangJae Lee, Heecheol Yang, Jonghak Choi

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

Comments 24 pages, 3 figures, 9 tables

MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models

Amirul Rahman, Qiang Xu, Xueying Huang

机构 * University of Malaya（马来大学） 纠错

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

From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning

Chalamalasetti Kranti, Sherzod Hakimov, David Schlangen

机构 * Computational Linguistics, Department of Linguistics University of Potsdam（乌特雷赫特大学语言学系计算语言学部） ； German Research Center for Artificial Intelligence (DFKI), Berlin（德国人工智能研究中心（DFKI）柏林） 纠错

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

Comments 17 pages

LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarios

Mingxing Peng, Yuting Xie, Xusen Guo, Ruoyu Yao, Hai Yang, Jun Ma

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院） 纠错

专题命中 视觉空间推理 ：chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI、cs.LG

Comments 18 pages, 8 figures

RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene Graph

Hecheng Wang, Jiankun Ren, Jia Yu, Lizhe Qi, Yunquan Sun

专题命中 视觉空间推理 ：reasoning(abstract)

Foundation Models for Zero-Shot Segmentation of Scientific Images without AI-Ready Data

Shubhabrata Mukherjee, Jack Lang, Obeen Kwon, Iryna Zenyuk, Valerie Brogden, Adam Weber, Daniela Ushizima

机构 * Lawrence Berkeley National Laboratory（伯克利国家实验室） ； University of California, Irvine（加州大学尔湾分校） ； University of California, Berkeley（加州大学伯克利分校） ； Covalent Metrology（协力计量） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments This paper has been accepted for presentation at the 59th International Conference on Parallel Processing (ICPP 2025), DRAI workshop

Learning Adaptive Parallel Reasoning with Language Models

Jiayi Pan, Xiuyu Li, Long Lian, Charlie Snell, Yifei Zhou, Adam Yala, Trevor Darrell, Kurt Keutzer, Alane Suhr

机构 * UC Berkeley（加州大学伯克利分校） ； UCSF（旧金山大学） 纠错

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

Comments Accepted at COLM 2025. Code, model, and data are available at https://github.com/Parallel-Reasoning/APR. The first three authors contributed equally to this work

Improving Text Style Transfer using Masked Diffusion Language Models with Inference-time Scaling

Tejomay Kishor Padole, Suyash P Awate, Pushpak Bhattacharyya

机构 * Dept. of Computer Science and Engineering, Indian Institute of Technology, Bombay（计算机科学与工程系，印度理工学院，孟买） 纠错

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

Comments Accepted as a main conference submission in the European Conference on Artificial Intelligence (ECAI 2025)

LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering

Xinxin Dong, Baoyun Peng, Haokai Ma, Yufei Wang, Zixuan Dong, Fei Hu, Xiaodong Wang

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

ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models

Yuanfeng Xu, Zehui Dai, Jian Liang, Jiapeng Guan, Guangrun Wang, Liang Lin, Xiaohui Lv

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

Comments 16pages, 3 figures

Overcoming Knowledge Discrepancies: Structuring Reasoning Threads through Knowledge Balancing in Interactive Scenarios

Daniel Burkhardt, Xiangwei Cheng

机构 * Ferdinand Steinbeis Institute（费尔迪南·斯坦贝茨研究所） 纠错

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

Comments 13 pages, 1 figure, 6 tables

Ovis2.5 Technical Report

Shiyin Lu, Yang Li, Yu Xia, Yuwei Hu, Shanshan Zhao, Yanqing Ma, Zhichao Wei, Yinglun Li, Lunhao Duan, Jianshan Zhao, Yuxuan Han, Haijun Li, Wanying Chen, Junke Tang, Chengkun Hou, Zhixing Du, Tianli Zhou, Wenjie Zhang, Huping Ding, Jiahe Li, Wen Li, Gui Hu, Yiliang Gu, Siran Yang, Jiamang Wang, Hailong Sun, Yibo Wang, Hui Sun, Jinlong Huang, Yuping He, Shengze Shi, Weihong Zhang, Guodong Zheng, Junpeng Jiang, Sensen Gao, Yi-Feng Wu, Sijia Chen, Yuhui Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang

机构 * Alibaba Group（阿里巴巴集团） 纠错

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

Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards

Ting Yang, Li Chen, Huimin Wang

机构 * Hong Kong Baptist University（香港 Baptist 大学） ； Jarvis Lab（Jarvis 实验室） 纠错

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

Q-FSRU: Quantum-Augmented Frequency-Spectral Fusion for Medical Visual Question Answering

Rakesh Thakur, Yusra Tariq

机构 * Amity Centre for Artificial Intelligence, Amity University, Noida（阿米蒂人工智能中心，阿米蒂大学，诺伊达） 纠错

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

Comments 8 pages, 4 figures Submitted to AAAI 26

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

Lajos Muzsai, David Imolai, András Lukács

机构 * Eötvös Loránd University, Institute of Mathematics, AI Research Group（埃奥武斯·洛尔兰大学数学学院人工智能研究组） 纠错

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

Comments 13 pages, 2 figures

Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering

Gongyao Jiang, Qiong Luo

机构 * The Hong Kong University of Science 纠错

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

Comments Accepted to CIKM 2025

From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

Jia Deng, Jie Chen, Zhipeng Chen, Daixuan Cheng, Fei Bai, Beichen Zhang, Yinqian Min, Yanzipeng Gao, Wayne Xin Zhao, Ji-Rong Wen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（北京理工大学人工智能学院） 纠错

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

Comments 27pages,25figures. arXiv admin note: text overlap with arXiv:2508.02260

DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Models

Xiaochuan Lin, Xiangyong Chen, Xuan Li, Yichen Su

机构 * Henan Polytechnic University（河南理工大学） 纠错

专题命中 复杂问题求解 ：CoT(abstract)

Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding

Zhifeng Kong, Arushi Goel, Joao Felipe Santos, Sreyan Ghosh, Rafael Valle, Wei Ping, Bryan Catanzaro

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

X-Ray-CoT: Interpretable Chest X-ray Diagnosis with Vision-Language Models via Chain-of-Thought Reasoning

Chee Ng, Liliang Sun, Shaoqing Tang

机构 * Universiti Teknologi Malaysia（马来西亚技术大学） 纠错

专题命中 推理评测 ：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(title,abstract)

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

Ke Niu, Haiyang Yu, Zhuofan Chen, Mengyang Zhao, Teng Fu, Bin Li, Xiangyang Xue

机构 * Fudan University（复旦大学） ； ByteDance Inc（字节跳动公司） 纠错

专题命中 推理评测 ：chain-of-thought(title,abstract)；reasoning(abstract)；CoT(abstract)；logical reasoning(abstract)

Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation

Yuheng Zha, Kun Zhou, Yujia Wu, Yushu Wang, Jie Feng, Zhi Xu, Shibo Hao, Zhengzhong Liu, Eric P. Xing, Zhiting Hu

机构 * UC San Diego（UC圣地亚哥大学） ； Carnegie Mellon University（卡内基梅隆大学） ； MBZUAI（马斯克人工智能研究所） 纠错

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

CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs

Hongtao Liu, Zhicheng Du, Zihe Wang, Weiran Shen

机构 * Gaoling School of Artificial Intelligence（北京语言大学人工智能学院） ； Renmin University of China（中国人民大学） 纠错

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

Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play

Lucia Cipolina-Kun, Marianna Nezhurina, Jenia Jitsev

机构 * LAION Juelich Supercomputing Center (JSC)（LAION尤利奇超级计算机中心（JSC）） ； Research Center Juelich (FZJ)（尤利奇研究中心（FZJ）） 纠错

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

Understanding Pedestrian Gesture Misrecognition: Insights from Vision-Language Model Reasoning

Tram Thi Minh Tran, Xinyan Yu, Callum Parker, Julie Stephany Berrio Perez, Stewart Worrall, Martin Tomitsch

专题命中 推理评测 ：reasoning(title,abstract)

ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images

Wenjie Liao, Jieyu Yuan, Yifang Xu, Chunle Guo, Zilong Zhang, Jihong Li, Jiachen Fu, Haotian Fan, Tao Li, Junhui Cui, Chongyi Li

机构 * Media Evaluation Lab, ByteDance Inc.（字节跳动公司媒体评估实验室） 纠错

专题命中 推理评测 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Breaking Language Barriers: Equitable Performance in Multilingual Language Models

Tanay Nagar, Grigorii Khvatskii, Anna Sokol, Nitesh V. Chawla

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校） ； NSF Center for Computer Assisted Synthesis (CCAS), University of Notre Dame（国家科学基金会计算机辅助合成中心（CCAS）、诺特大学） ； University of Notre Dame（诺特大学） 纠错

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

Comments Accepted as a non-archival work-in-progress paper at the NAACL 2025 Student Research Workshop

The Self-Execution Benchmark: Measuring LLMs' Attempts to Overcome Their Lack of Self-Execution

Elon Ezra, Ariel Weizman, Amos Azaria

机构 * School of Computer Science, Ariel University（计算机科学学院，阿维夫大学） 纠错

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

Comments 11 pages, 9 figures