大模型推理能力

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Weihao Tan, Xiangyang Li, Yunhao Fang, Heyuan Yao, Shi Yan, Hao Luo, Tenglong Ao, Huihui Li, Hongbin Ren, Bairen Yi, Yujia Qin, Bo An, Libin Liu, Guang Shi

机构 * ByteDance Seed（字节跳动种子） ； NTU（国立科技大学） 纠错

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

Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation

Sicheng Yang, Yukai Huang, Weitong Cai, Shitong Sun, You He, Jiankang Deng, Hang Zhang, Jifei Song, Zhensong Zhang

专题命中 视觉空间推理 ：reasoning(abstract)

Comments 16 pages, 9 figures, AAAI 2026

RL-U$^2$Net: A Dual-Branch UNet with Reinforcement Learning-Assisted Multimodal Feature Fusion for Accurate 3D Whole-Heart Segmentation

Jierui Qu, Jianchun Zhao

专题命中 视觉空间推理 ：planning(abstract)

Crafting Dynamic Virtual Activities with Advanced Multimodal Models

Changyang Li, Qingan Yan, Minyoung Kim, Zhan Li, Yi Xu, Lap-Fai Yu

专题命中 视觉空间推理 ：reasoning(abstract)

Journal ref C. Li, Q. Yan, M. Kim, Z. Li, Y. Xu and L. -F. Yu, "Crafting Dynamic Virtual Activities with Advanced Multimodal Models," 2025 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 120-130

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

Juyuan Wang, Rongchen Zhao, Wei Wei, Yufeng Wang, Mo Yu, Jie Zhou, Jin Xu, Liyan Xu

机构 * Tencent（腾讯） 纠错

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

Comments Accepted by AAAI 2026

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning

Jiawei Zhang, Shuang Yang, Bo Li

机构 * Department of Computer Science, University of Chicago（芝加哥大学计算机科学系） ； Meta ； Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系） 纠错

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

When Reasoning Fails: Evaluating 'Thinking' LLMs for Stock Prediction

Rakeshkumar H Sodha

专题命中 复杂问题求解 ：reasoning(title,abstract)

Self-Correcting Large Language Models: Generation vs. Multiple Choice

Hossein A. Rahmani, Satyapriya Krishna, Xi Wang, Mohammadmehdi Naghiaei, Emine Yilmaz

机构 * University College London（伦敦大学学院） ； Amazon AGI（亚马逊人工智能实验室） ； University of Sheffield（谢菲尔德大学） ； University of Southern California（南加州大学） 纠错

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

Comments 20 pages

Solving a Million-Step LLM Task with Zero Errors

Elliot Meyerson, Giuseppe Paolo, Roberto Dailey, Hormoz Shahrzad, Olivier Francon, Conor F. Hayes, Xin Qiu, Babak Hodjat, Risto Miikkulainen

机构 * Cognizant AI Lab（Cognizant AI实验室） ； UT Austin（得克萨斯大学奥斯汀分校） 纠错

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

Comments Main paper: 14 pages, 29 pages with references and appendix

AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems

Rohan Kadekodi, Zhan Jin, Keisuke Kamahori, Yile Gu, Sean Khatiri, Noah H. Bayindirli, Sergey Gorbunov, Baris Kasikci

机构 * University of Washington（华盛顿大学） ； Peking University（北京大学） ； University of Waterloo（滑铁卢大学） ； Interop Labs（Interop实验室） 纠错

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

Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling

Sydney Anuyah, Mehedi Mahmud Kaushik, Krishna Dwarampudi, Rakesh Shiradkar, Arjan Durresi, Sunandan Chakraborty

机构 * Indiana University（印第安纳大学） ； Purdue University（普渡大学） ； Department of Biomedical Engineering（生物医学工程系） ； Informatics, Indiana University（印第安纳大学信息学院） 纠错

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

Knowledge Graph Analysis of Legal Understanding and Violations in LLMs

Abha Jha, Abel Salinas, Fred Morstatter

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

When AI Takes the Wheel: Security Analysis of Framework-Constrained Program Generation

Yue Liu, Zhenchang Xing, Shidong Pan, Chakkrit Tantithamthavorn

专题命中 复杂问题求解 ：reasoning(abstract)

EgoTV: Egocentric Task Verification from Natural Language Task Descriptions

Rishi Hazra, Brian Chen, Akshara Rai, Nitin Kamra, Ruta Desai

机构 * Örebro University（奥雷布罗大学） ； Meta 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Accepted at ICCV 2023

Mitigating Hallucinations in Large Language Models via Causal Reasoning

Yuangang Li, Yiqing Shen, Yi Nian, Jiechao Gao, Ziyi Wang, Chenxiao Yu, Shawn Li, Jie Wang, Xiyang Hu, Yue Zhao

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

e1: Learning Adaptive Control of Reasoning Effort

Michael Kleinman, Matthew Trager, Alessandro Achille, Wei Xia, Stefano Soatto

机构 * AWS Agentic AI（AWS智能人工智能） 纠错

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

AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting

Renda Li, Hailang Huang, Fei Wei, Feng Xiong, Yong Wang, Xiangxiang Chu

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

mmJEE-Eval: A Bilingual Multimodal Benchmark for Evaluating Scientific Reasoning in Vision-Language Models

Arka Mukherjee, Shreya Ghosh

机构 * Kalinga Institute of Industrial Technology (KIIT)（喀里亚理工学院） ； Indian Institute of Technology (IIT), Bhubaneswar（印度理工学院（班加罗尔）） 纠错

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

Comments Accepted to IJCNLP-AACL Findings 2025

LLM-Guided Dynamic-UMAP for Personalized Federated Graph Learning

Sai Puppala, Ismail Hossain, Md Jahangir Alam, Tanzim Ahad, Sajedul Talukder

机构 * University of Texas at El Paso（德克萨斯理工大学） ； Southern Illinois University Carbondale（南方伊利诺伊大学卡本代尔分校） 纠错

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

MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique

Gailun Zeng, Ziyang Luo, Hongzhan Lin, Yuchen Tian, Kaixin Li, Ziyang Gong, Jianxiong Guo, Jing Ma

机构 * Hong Kong Baptist University（香港 Baptist 大学） ； Beijing Normal-Hong Kong Baptist University（北京师范大学-香港 Baptist 大学） ； National University of Singapore（新加坡国立大学） ； Beijing Normal University（北京师范大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

Comments 28 pages, 14 figures, 19 tables

SynClaimEval: A Framework for Evaluating the Utility of Synthetic Data in Long-Context Claim Verification

Mohamed Elaraby, Jyoti Prakash Maheswari

机构 * University of Pittsburgh（匹兹堡大学） ； Zillow Inc.（Zillow公司） 纠错

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

Journal ref The 5th Workshop on Evaluation & Comparison of NLP Systems, 2025

Towards Explainable Khmer Polarity Classification

Marry Kong, Rina Buoy, Sovisal Chenda, Nguonly Taing

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

FLAD: Federated Learning for LLM-based Autonomous Driving in Vehicle-Edge-Cloud Networks

Tianao Xiang, Mingjian Zhi, Yuanguo Bi, Lin Cai, Yuhao Chen

机构 * Northeastern University（东北大学） ； University of Victoria（维多利亚大学） 纠错

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

BioVerge: A Comprehensive Benchmark and Study of Self-Evaluating Agents for Biomedical Hypothesis Generation

Fuyi Yang, Chenchen Ye, Mingyu Derek Ma, Yijia Xiao, Matthew Yang, Wei Wang

机构 * University of California, Los Angeles（加州大学洛杉矶分校） 纠错

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

PISA-Bench: The PISA Index as a Multilingual and Multimodal Metric for the Evaluation of Vision-Language Models

Patrick Haller, Fabio Barth, Jonas Golde, Georg Rehm, Alan Akbik

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

Comments 8 pages, 11 tables and figures

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation

Mariia Drozdova, Erica Lastufka, Vitaliy Kinakh, Taras Holotyak, Daniel Schaerer, Slava Voloshynovskiy

机构 * University of Geneva（日内瓦大学） 纠错

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

Comments Machine Learning and the Physical Sciences Workshop, NeurIPS 2025

OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation

Hanning Zhang, Juntong Song, Juno Zhu, Yuanhao Wu, Tong Zhang, Cheng Niu

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

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

Comments Preprint update

The LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications

Gaëtan Caillaut, Raheel Qader, Jingshu Liu, Mariam Nakhlé, Arezki Sadoune, Massinissa Ahmim, Jean-Gabriel Barthelemy

机构 * Dragon LLM 纠错

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

Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models

Daniyal Ganiuly, Assel Smaiyl

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

Comments 10 pages, 6 figures

VietMEAgent: Culturally-Aware Few-Shot Multimodal Explanation for Vietnamese Visual Question Answering

Hai-Dang Nguyen, Minh-Anh Dang, Minh-Tan Le, Minh-Tuan Le

机构 * Faculty Of Information Technology, VNU University of Engineering and Technology（信息科技学院，越南工程与技术大学） ； IT-BT Convergence Technology Division, Vietnam-Korea Institute of Science and Technology（IT-BT融合技术部，越南-韩国科学技术院） ； TADI Global Lab, TADI Global Company Limited（TADI全球实验室，TADI全球公司） ； Faculty of Finance, Banking Academy of Vietnam（金融学院，越南银行学院） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments 7 pages, 3 figures, 3 tables, FAIR 2025 conference