大模型推理能力

Still Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?

Kunal Kingkar Das, Manoj Balaji Jagadeeshan, Nallani Chakravartula Sahith, Jivnesh Sandhan, Pawan Goyal

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

MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applications

Zike Yuan, Ming Liu, Hui Wang, Bing Qin

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Peng Cheng Laboratory（鹏城实验室） 纠错

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

UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist

Zhengyang Liang, Daoan Zhang, Huichi Zhou, Rui Huang, Bobo Li, Yuechen Zhang, Shengqiong Wu, Xiaohan Wang, Jiebo Luo, Lizi Liao, Hao Fei

机构 * Singapore Management University（新加坡管理大学） ； University of Rochester（罗切斯特大学） ； University College London（伦敦大学学院） ； National University of Singapore（新加坡国立大学） ； The Chinese University of Hong Kong（香港中文大学） ； Stanford University（斯坦福大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Technical Report. 24 figures, 37 pages. Website: https://univa.online/

Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter

Zhiyang Chen, Chen Zhang, Hao Fang, Runmin Cong

专题命中 复杂问题求解 ：reasoning(abstract)

Comments AAAI 2026

A Two-Stage System for Layout-Controlled Image Generation using Large Language Models and Diffusion Models

Jan-Hendrik Koch, Jonas Krumme, Konrad Gadzicki

机构 * Cognitive Neuroinformatics University of Bremen（认知神经信息学不莱梅大学） 纠错

专题命中 复杂问题求解 ：planning(abstract)

Comments 12 pages, 5 figures

VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Xinhao Li, Ziang Yan, Desen Meng, Lu Dong, Xiangyu Zeng, Yinan He, Yali Wang, Yu Qiao, Yi Wang, Limin Wang

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； Nanjing University（南京大学） ； Zhejiang University（浙江大学） ； University of Science and Technology of China（中国科学技术大学） ； Shanghai Innovation Institute（上海创新研究院） ； Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs

Chenqian Le, Ziheng Gong, Chihang Wang, Haowei Ni, Panfeng Li, Xupeng Chen

机构 * New York University（纽约大学） ； Columbia University（哥伦比亚大学） ； University of Michigan（密歇根大学） 纠错

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

Comments Accepted by 2025 International Conference on Artificial Intelligence, Human-Computer Interaction and Natural Language Processing

Journal ref Proceedings of the 2025 International Conference on Artificial Intelligence, Human-Computer Interaction and Natural Language Processing (ICAHN), 2025, pp. 43-46

DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry

Changti Wu, Shijie Lian, Zihao Liu, Lei Zhang, Laurence Tianruo Yang, Kai Chen

机构 * East China Normal University（华东师范大学） ； Zhongguancun Academy（中关村学院） ； Huazhong University of Science and Technology（华中科技大学） ； Peking University（北京大学） ； Zhengzhou University（郑州大学） ； Zhongguancun Institute of Artificial Intelligence（中关村人工智能研究院） 纠错

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

Comments The code and dataset are available at \href{https://zgca-ai4edu.github.io/DynaSolidGeo/}{DynaSolidGeo}

Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages

Max Zuo, Francisco Piedrahita Velez, Xiaochen Li, Michael L. Littman, Stephen H. Bach

机构 * Brown University（布朗大学） 纠错

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

Comments NAACL Main Conference 2025

Journal ref Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data

Zijun Wang, Haoqin Tu, Yuhan Wang, Juncheng Wu, Yanqing Liu, Jieru Mei, Brian R. Bartoldson, Bhavya Kailkhura, Cihang Xie

机构 * UC Santa Cruz（加州大学圣克ruz分校） ； Google（谷歌） ； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室） 纠错

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

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective

Songsong Yu, Yuxin Chen, Hao Ju, Lianjie Jia, Fuxi Zhang, Shaofei Huang, Yuhan Wu, Rundi Cui, Binghao Ran, Zaibin Zhang, Zhedong Zheng, Zhipeng Zhang, Yifan Wang, Lin Song, Lijun Wang, Yanwei Li, Ying Shan, Huchuan Lu

机构 * ARC Lab, Tencent PCG（腾讯PCG部门ARC实验室） ； Shanghai Jiao Tong University（上海交通大学） ； University of Macau（澳门大学） ； Dalian University of Technology（大连理工大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Comments a comprehensive visual spatial reasoning evaluation tool, 25 pages, 16 figures

SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation

Berkcan Kapusuzoglu, Supriyo Chakraborty, Renkun Ni, Stephen Rawls, Sambit Sahu

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

ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents

Manasi Sharma, Chen Bo Calvin Zhang, Chaithanya Bandi, Clinton Wang, Ankit Aich, Huy Nghiem, Tahseen Rabbani, Ye Htet, Brian Jang, Sumana Basu, Aishwarya Balwani, Denis Peskoff, Marcos Ayestaran, Sean M. Hendryx, Brad Kenstler, Bing Liu

机构 * Scale AI ； University of Maryland（马里兰大学） ； University of Chicago（芝加哥大学） ； Washington University, St. Louis（圣路易斯华盛顿大学） ； McGill University（麦吉尔大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

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

Comments 27 pages, 21 figures, pre-print

On the generalization of language models from in-context learning and finetuning: a controlled study

Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan, Cody Wild, Diane Wan, Alex Ku, Jörg Bornschein, Razvan Pascanu, Murray Shanahan, James L. McClelland

机构 * Google DeepMind（谷歌DeepMind） ； Google DeepMind & Stanford University（谷歌DeepMind与斯坦福大学） 纠错

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

Comments FoRLM workshop, NeurIPS 2025

Towards Outcome-Oriented, Task-Agnostic Evaluation of AI Agents

Waseem AlShikh, Muayad Sayed Ali, Brian Kennedy, Dmytro Mozolevskyi

机构 * Writer, Inc.（Writer公司） 纠错

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

NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation

Maoqi Liu, Quan Fang, Yuhao Wu, Can Zhao, Yang Yang, Kaiquan Cai

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

Comments Accepted to AAAI 2026

A Multimodal Recaptioning Framework to Account for Perceptual Diversity Across Languages in Vision-Language Modeling

Kyle Buettner, Jacob T. Emmerson, Adriana Kovashka

机构 * Intelligent Systems Program（智能系统项目） ； Department of Computer Science（计算机科学系） 纠错

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

Comments Accepted at IJCNLP-AACL 2025 (Main)

Beyond the Pixels: VLM-based Evaluation of Identity Preservation in Reference-Guided Synthesis

Aditi Singhania, Krutik Malani, Riddhi Dhawan, Arushi Jain, Garv Tandon, Nippun Sharma, Souymodip Chakraborty, Vineet Batra, Ankit Phogat

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

Towards a Standard, Enterprise-Relevant Agentic AI Benchmark: Lessons from 5.5 billion tokens' worth of agentic AI evaluations

JV Roig

机构 * Kamiwaza AI 纠错

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

Comments 34 pages

Generalizable Insights for Graph Transformers in Theory and Practice

Timo Stoll, Luis Müller, Christopher Morris

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

Comments Accepted at NeurIPS 2025 as spotlight

CellARC: Measuring Intelligence with Cellular Automata

Miroslav Lžičař

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

Comments 22 pages, 11 figures. Working draft. Dataset and leaderboard available at https://cellarc.mireklzicar.com

Design, Results and Industry Implications of the World's First Insurance Large Language Model Evaluation Benchmark

Hua Zhou, Bing Ma, Yufei Zhang, Yi Zhao

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

Comments 16 pages, 11 models,1 set of evaluation framework,5 core dimensions, 54 sub-indicators, 14,430 high-quality questions

3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark

Ivan Sviridov, Amina Miftakhova, Artemiy Tereshchenko, Galina Zubkova, Pavel Blinov, Andrey Savchenko

机构 * Sber AI Lab（Sber AI实验室） ； HSE University（俄罗斯高等经济大学） ； ISP RAS Research Center for Trusted Artificial Intelligence（俄罗斯科学院信息与系统问题研究所可信人工智能研究中心） 纠错

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

Comments EMNLP 25 (main)

Journal ref https://aclanthology.org/2025.emnlp-main.1353/

VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation

Arpan Phukan, Anupam Pandey, Deepjyoti Bodo, Asif Ekbal

机构 * Department of Computer Science and Engineering, IIT Patna（计算机科学与工程系，印度理工学院帕纳） 纠错

专题命中 推理评测 ：reasoning(abstract)

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

Yaxuan Wang, Chris Yuhao Liu, Quan Liu, Jinglong Pang, Wei Wei, Yujia Bao, Yang Liu

机构 * University of California, Santa Cruz（加州大学圣克ruz分校） ； Center for Advanced AI, Accenture（Accenture高级人工智能中心） 纠错

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

Comments Please refer to the NeurIPS 2025 submission: https://openreview.net/forum?id=FNuul0hlin The paper has been accepted to the ICML 2025 MUGen Workshop: https://openreview.net/forum?id=ET24oKP23c

Dual-Process Scaffold Reasoning for Enhancing LLM Code Debugging

Po-Chung Hsieh, Chin-Po Chen, Jeng-Lin Li, Ming-Ching Chang

机构 * National Taiwan University（国立台湾大学） ； AI Research Center, Inventec Corporation（Inventec公司人工智能研究中心） ； University at Albany, SUNY（纽约州立大学阿尔巴尼分校） 纠错

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

Comments 5 pages, 2 figures

Neurophysiological Characteristics of Adaptive Reasoning for Creative Problem-Solving Strategy

Jun-Young Kim, Young-Seok Kweon, Gi-Hwan Shin, Seong-Whan Lee

机构 * Dept. of Artificial Intelligence（人工智能系） ； Korea University（韩国大学） ； Dept. of Brain and Cognitive Engineering（脑科学与认知工程系） 纠错

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

Comments 4 pages, 4 figures, 1 table,

OneRec-Think: In-Text Reasoning for Generative Recommendation

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, Pengfei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zixing Zhang, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

专题命中 其他推理 ：reasoning(title,abstract)

UniFormer: Unified and Efficient Transformer for Reasoning Across General and Custom Computing

Zhuoheng Ran, Chong Wu, Renjie Xu, Maolin Che, Hong Yan

专题命中 其他推理 ：reasoning(title,comments)

Comments Accepted on 24 September 2025 at NeurIPS 2025 Efficient Reasoning Workshop

PerspAct: Enhancing LLM Situated Collaboration Skills through Perspective Taking and Active Vision

Sabrina Patania, Luca Annese, Anita Pellegrini, Silvia Serino, Anna Lambiase, Luca Pallonetto, Silvia Rossi, Simone Colombani, Tom Foulsham, Azzurra Ruggeri, Dimitri Ognibene

机构 * University of Milan-Bicocca（米兰-比科卡大学） ； University of Naples Federico II（那不勒斯费德里科二世大学） ； Oversonic Robotics（Oversonic机器人公司） ； University of Essex（埃塞克斯大学） ； TUM School of Social Sciences and Technology（慕尼黑技术大学社会科学与技术学院） 纠错

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

Comments Accepted at IAS19