大模型推理能力

SABER: Switchable and Balanced Training for Efficient LLM Reasoning

Kai Zhao, Yanjun Zhao, Jiaming Song, Shien He, Lusheng Zhang, Qiang Zhang, Tianjiao Li

专题命中 数学推理 ：reasoning(title,abstract)；chain-of-thought(abstract)；math reasoning(abstract)；logical reasoning(abstract)

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

Runqi Qiao, Qiuna Tan, Peiqing Yang, Yanzi Wang, Xiaowan Wang, Enhui Wan, Sitong Zhou, Guanting Dong, Yuchen Zeng, Yida Xu, Jie Wang, Chong Sun, Chen Li, Honggang Zhang

机构 * BUPT（北京邮电大学） ； WeChat Vision, Tencent Inc.（腾讯公司） ； Tsinghua University（清华大学） 纠错

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

Comments Working in progress

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization

Xingyu Wu, Yuchen Yan, Shangke Lyu, Linjuan Wu, Yiwen Qiu, Yongliang Shen, Weiming Lu, Jian Shao, Jun Xiao, Yueting Zhuang

机构 * Zhejiang University（浙江大学） 纠错

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

Comments GitHub:https://github.com/zju-real/lapoProject:https://zju-real.github.io/lapo

Mathematical Computation and Reasoning Errors by Large Language Models

Liang Zhang, Edith Aurora Graf

机构 * Institute for Intelligent Systems（智能系统研究所） ； University of Memphis（密苏里大学） ； AI4STEM Education Center（AI4STEM教育中心） ； University of Georgia（佐治亚大学） ； Educational Testing Service（教育测量服务） 纠错

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

ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs

Keyu Chen, Zhifeng Shen, Daohai Yu, Haoqian Wu, Wei Wen, Jianfeng He, Ruizhi Qiao, Xing Sun

机构 * Youtu Team（你Tube团队） 纠错

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

Comments 20 pages, 9 figures

CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization

Yanxia Deng, Aozhong Zhang, Selcuk Gurses, Naigang Wang, Zi Yang, Penghang Yin

机构 * Department of Mathematics and Statistics（数学与统计学系） ； University at Albany, SUNY（阿尔巴尼大学） ； IBM T. J. Watson Research Center（IBM 塔沃森研究中心） 纠错

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

Journal ref Transactions on Machine Learning Research (TMLR), 2025

NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning

Zhixi Cai, Fucai Ke, Simindokht Jahangard, Maria Garcia de la Banda, Reza Haffari, Peter J. Stuckey, Hamid Rezatofighi

机构 * Monash University（莫纳什大学） 纠错

专题命中 逻辑推理 ：reasoning(title,abstract)

Comments ICCV 2025

Can Transformers Break Encryption Schemes via In-Context Learning?

Jathin Korrapati, Patrick Mendoza, Aditya Tomar, Abein Abraham

机构 * UC Berkeley（伯克利大学） 纠错

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

Performance of GPT-5 in Brain Tumor MRI Reasoning

Mojtaba Safari, Shansong Wang, Mingzhe Hu, Zach Eidex, Qiang Li, Xiaofeng Yang

机构 * Department of Radiation Oncology, Winship Cancer Institute, Emory University School of Medicine（放射肿瘤科，Winship癌症研究所，埃默里大学医学院） 纠错

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

SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks

Pengbo Shen, Yaqing Wang, Ni Mu, Yao Luan, Runpeng Xie, Senhao Yang, Lexiang Wang, Hao Hu, Shuang Xu, Yiqin Yang, Bo Xu

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；verifier(abstract)；self-correction(abstract)

TLE-Based A2C Agent for Terrestrial Coverage Orbital Path Planning

Anantha Narayanan, Battu Bhanu Teja, Pruthwik Mishra

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

Comments 8 pages, 6 figures, 5 tables

Measuring Time Series Forecast Stability for Demand Planning

Steven Klee, Yuntian Xia

机构 * Amazon Web Services（亚马逊网络服务） 纠错

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

Comments 6 pages, 3 figures; KDD '25

A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation

Jiulin Li, Ping Huang, Yexin Li, Shuo Chen, Juewen Hu, Ye Tian

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

Comments 8 pages, 5 figures

X-Node: Self-Explanation is All We Need

Prajit Sengupta, Islem Rekik

机构 * BASIRA Lab, Imperial-X (I-X)（BASIRA实验室，Imperial-X（I-X）） ； Department of Computing, Imperial College London, London, United Kingdom（计算系，伦敦帝国学院，伦敦，英国） 纠错

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

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods

Isha Puri, Shivchander Sudalairaj, Guangxuan Xu, Kai Xu, Akash Srivastava

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） ； RedHat AI Innovation（红帽人工智能创新） 纠错

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

Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning

Wenlong Liang, Rui Zhou, Yang Ma, Bing Zhang, Songlin Li, Yijia Liao, Ping Kuang

机构 * University of Electronic Science and Technology of China（电子科技大学） 纠错

专题命中 规划推理 ：planning(abstract)

A Semantic-Aware Framework for Safe and Intent-Integrative Assistance in Upper-Limb Exoskeletons

Yu Chen, Shu Miao, Chunyu Wu, Jingsong Mu, Bo OuYang, Xiang Li

机构 * Department of Automation, Tsinghua University（自动化系，清华大学） 纠错

专题命中 规划推理 ：planning(abstract)

CarAT: Carbon Atom Tracing across Industrial Chemical Value Chains via Chemistry Language Models

Emma Pajak, David Walz, Olga Walz, Laura Marie Helleckes, Klaus Hellgardt, Antonio del Rio Chanona

专题命中 规划推理 ：planning(abstract)

Comments 21 pages, 9 figures, pre-print

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Atin Pothiraj, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

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

Comments ICCV 2025

Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs

Dehao Tao, Guangjie Liu, Weizheng, Yongfeng Huang, Minghu jiang

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

Warehouse Spatial Question Answering with LLM Agent

Hsiang-Wei Huang, Jen-Hao Cheng, Kuang-Ming Chen, Cheng-Yen Yang, Bahaa Alattar, Yi-Ru Lin, Pyongkun Kim, Sangwon Kim, Kwangju Kim, Chung-I Huang, Jenq-Neng Hwang

机构 * Information Processing Lab, University of Washington, USA（华盛顿大学信息处理实验室） ； Electronics and Telecommunications Research Institute, South Korea（韩国电子电信研究院） ； National Center for High-performance Computing, Taiwan（台湾高性能计算国家研究中心） 纠错

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

Comments 1st Place Solution of the 9th AI City Challenge Track 3

SpaRC-AD: A Baseline for Radar-Camera Fusion in End-to-End Autonomous Driving

Philipp Wolters, Johannes Gilg, Torben Teepe, Gerhard Rigoll

机构 * Technical University of Munich（慕尼黑技术大学） 纠错

专题命中 视觉空间推理 ：planning(abstract)

Comments 8 pages, 4 figures, 5 tables

MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models

Jian Chen, Wenye Ma, Penghang Liu, Wei Wang, Tengwei Song, Ming Li, Chenguang Wang, Jiayu Qin, Ruiyi Zhang, Changyou Chen

专题命中 视觉空间推理 ：reasoning(abstract)

Comments Under Review

RTTC: Reward-Guided Collaborative Test-Time Compute

J. Pablo Muñoz, Jinjie Yuan

机构 * Intel Labs Santa Clara, CA, USA（英特尔圣克拉拉实验室） ； Intel Corporation Beijing, China（英特尔北京公司） 纠错

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

The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference

Maël Jullien, Marco Valentino, André Freitas

机构 * Department of Computer Science, University of Manchester, UK（曼彻斯特大学计算机科学系） ； National Biomarker Centre, CRUK-MI, University of Manchester, UK（曼彻斯特大学国家生物标志物中心） ； Idiap Research Institute, Switzerland（日内瓦IDIAP研究所） ； School of Computer Science, University of Sheffield, UK（谢菲尔德大学计算机科学学院） 纠错

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

Comments 19 pages

RealAC: A Domain-Agnostic Framework for Realistic and Actionable Counterfactual Explanations

Asiful Arefeen, Shovito Barua Soumma, Hassan Ghasemzadeh

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

TextQuests: How Good are LLMs at Text-Based Video Games?

Long Phan, Mantas Mazeika, Andy Zou, Dan Hendrycks

机构 * Center for AI Safety（人工智能安全中心） ； Carnegie Mellon University（卡内基梅隆大学） ； Gray Swan AI（灰天鹅AI） 纠错

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

Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis

Linqing Chen, Hanmeng Zhong, Wentao Wu, Weilei Wang

机构 * Linqing Chen, Hanmeng Zhong, Wentao Wu, Weilei Wang（作者） 纠错

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

IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection

Yanhui Li, Yunkang Cao, Chengliang Liu, Yuan Xiong, Xinghui Dong, Chao Huang

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

What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles

Mengtao Zhou, Sifan Wu, Huan Zhang, Qi Sima, Bang Liu

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