大模型推理能力

Enabling Few-Shot Alzheimer's Disease Diagnosis on Biomarker Data with Tabular LLMs

Sophie Kearney, Shu Yang, Zixuan Wen, Bojian Hou, Duy Duong-Tran, Tianlong Chen, Jason Moore, Marylyn Ritchie, Li Shen

机构 * University of Pennsylvania（宾夕法尼亚大学） ； United States Naval Academy（美国海军学院） ； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Cedars Sinai Medical Center（西好莱坞 Cedars Sinai 医院） 纠错

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

Comments accepted by ACM-BCB'25: ACM Conference on Bioinformatics, Computational Biology, and Health Informatics [ACM SIGBio Best Paper Award]

Discursive Circuits: How Do Language Models Understand Discourse Relations?

Yisong Miao, Min-Yen Kan

机构 * Web IR / NLP Group (WING)（网络信息检索与自然语言处理组） 纠错

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

Comments Accepted to EMNLP 2025 (Main Conference); 9 pages, 8 figures, 5 tables (20 pages, 12 figures, 14 tables including references and appendices)

CALM: A Causal Analysis Language Model for Tabular Data in Complex Systems with Local Scores, Conditional Independence Tests, and Relation Attributes

Zhenjiang Fan, Zengyi Qin, Yuanning Zheng, Bo Xiong, Summer Han

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

Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)

Lucas Carrit Delgado Pinheiro, Ziru Chen, Bruno Caixeta Piazza, Ness Shroff, Yingbin Liang, Yuan-Sen Ting, Huan Sun

机构 * The Ohio State University（俄亥俄州立大学） ； Universidade de São Paulo（圣保罗大学） 纠错

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

Comments 18 pages, 6 figures, to be submitted, comments are welcome. Reproducibility details can be found at: https://github.com/OSU-NLP-Group/LLM-IOAA

TravelBench : Exploring LLM Performance in Low-Resource Domains

Srinivas Billa, Xiaonan Jing

机构 * Expedia Group（Expedia集团） 纠错

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

Comments 10 pages, 3 figures

Continuous Thought Machines

Luke Darlow, Ciaran Regan, Sebastian Risi, Jeffrey Seely, Llion Jones

机构 * Sakana AI ； University of Tsukuba（东京大学） ； IT University of Copenhagen（哥本哈根IT大学） 纠错

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

Comments Technical report accompanied by online project page: https://pub.sakana.ai/ctm/ Accepted as a spotlight paper at NeurIPS 2025

Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training

Yao-Ching Yu, Tsun-Han Chiang, Cheng-Wei Tsai, Chien-Ming Huang, Wen-Kwang Tsao

机构 * AI Lab, TrendMicro（TrendMicro人工智能实验室） 纠错

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

Comments Accepted to EMNLP 2025

RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs

Can Lin, Zhengwang Jiang, Ling Zheng, Qi Zhao, Yuhang Zhang, Qi Song, Wangqiu Zhou

机构 * University of Science and Technology of China（中国科学技术大学） ； City University of Hong Kong（香港城市大学） ； Deqing Alpha Innovation Institute（德清Alpha创新研究院） ； Hefei University of Technology（合肥工业大学） 纠错

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

Comments 18 pages, 9 figures

QSpec: Speculative Decoding with Complementary Quantization Schemes

Juntao Zhao, Wenhao Lu, Sheng Wang, Lingpeng Kong, Chuan Wu

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

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025)

BroRL: Scaling Reinforcement Learning via Broadened Exploration

Jian Hu, Mingjie Liu, Ximing Lu, Fang Wu, Zaid Harchaoui, Shizhe Diao, Yejin Choi, Pavlo Molchanov, Jun Yang, Jan Kautz, Yi Dong

机构 * NVIDIA ； Stanford University（斯坦福大学） ； University of Washington（华盛顿大学） 纠错

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

Comments 16 pages, 4 figures

Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks

Peiran Xu, Zhuohao Li, Xiaoying Xing, Guannan Zhang, Debiao Li, Kunyu Shi

机构 * Accio Team, Alibaba Group（阿里集团阿西莫团队） ； University of California, Los Angeles (UCLA)（加州大学洛杉矶分校） 纠错

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

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution

Tianrui Qin, Qianben Chen, Sinuo Wang, He Xing, King Zhu, He Zhu, Dingfeng Shi, Xinxin Liu, Ge Zhang, Jiaheng Liu, Yuchen Eleanor Jiang, Xitong Gao, Wangchunshu Zhou

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

Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents

Khanh Trinh Pham, Thu Huong Nguyen, Jun Jo, Quoc Viet Hung Nguyen, Thanh Tam Nguyen

机构 * Griffith University（格里菲斯大学） 纠错

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

A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models

Qinggang Zhang, Shengyuan Chen, Yuanchen Bei, Zheng Yuan, Huachi Zhou, Zijin Hong, Hao Chen, Yilin Xiao, Chuang Zhou, Junnan Dong, Yi Chang, Xiao Huang

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

From Grunts to Lexicons: Emergent Language from Cooperative Foraging

Maytus Piriyajitakonkij, Rujikorn Charakorn, Weicheng Tao, Wei Pan, Mingfei Sun, Cheston Tan, Mengmi Zhang

机构 * Institute for Infocomm Research (I 2 {}^{\text{2}} R), A ∗ STAR, Singapore（新加坡信息与通信研究院） ； College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机科学与数据科学学院） ； Department of Computer Science, The University of Manchester, United Kingdom（曼彻斯特大学计算机科学系） ； Centre for Frontier AI Research (CFAR), A ∗ STAR, Singapore（前沿人工智能研究中心） ； Sakana AI, Japan（日本Sakana AI） 纠错

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

DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding

Kin Ian Lo, Hala Hawashin, Mina Abbaszadeh, Tilen Limback-Stokin, Hadi Wazni, Mehrnoosh Sadrzadeh

机构 * University College London（伦敦大学学院） 纠错

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

Causal Reflection with Language Models

Abi Aryan, Zac Liu

机构 * Abide AI 纠错

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

Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI

Lorenzo Giusti, Ole Anton Werner, Riccardo Taiello, Matilde Carvalho Costa, Emre Tosun, Andrea Protani, Marc Molina, Rodrigo Lopes de Almeida, Paolo Cacace, Diogo Reis Santos, Luigi Serio

机构 * CERN（欧洲核子研究中心） 纠错

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

Comments 18 pages, 4 figures

Embodied AI: From LLMs to World Models

Tongtong Feng, Xin Wang, Yu-Gang Jiang, Wenwu Zhu

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心） ； Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院） 纠错

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

Comments Accepted by IEEE CASM

Interaction Topological Transformer for Multiscale Learning in Porous Materials

Dong Chen, Jian Liu, Chun-Long Chen, Guo-Wei Wei

机构 * Department of Mathematics, Michigan State University（数学系，密歇根州立大学） ； Physical Sciences Division, Pacific Northwest National Laboratory（物理科学部，太平洋西北国家实验室） ； Department of Electrical and Computer Engineering, Michigan State University（电气与计算机工程系，密歇根州立大学） ； Department of Biochemistry and Molecular Biology, Michigan State University（生物化学与分子生物学系，密歇根州立大学） 纠错

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

Comments 4 figures, 2 tables

Can Language Models Follow Multiple Turns of Entangled Instructions?

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of California San Diego（加州大学圣地亚哥分校） 纠错

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

Comments The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) Findings

Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech

Sang Hoon Woo, Sehun Lee, Kang-wook Kim, Gunhee Kim

机构 * Seoul National University（首尔国立大学） 纠错

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

Comments EMNLP 2025 Main. Project page: https://yhytoto12.github.io/TVS-ReVerT

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing

Zichen Wu, Hsiu-Yuan Huang, Yunfang Wu

机构 * School of Computer Science, Peking University（北京大学计算机科学学院） ； MOE Key Laboratory of Computational Linguistics, Peking University（北京大学教育部计算语言学重点实验室） ； National Key Laboratory for Multimedia Information Processing, Peking University（北京大学国家多媒体信息处理重点实验室） 纠错

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

Comments Accepted by EMNLP 2025 Findings

Combating Biomedical Misinformation through Multi-modal Claim Detection and Evidence-based Verification

Mariano Barone, Antonio Romano, Giuseppe Riccio, Marco Postiglione, Vincenzo Moscato

机构 * University of Naples Federico II（那不勒斯费迪里奇二世大学） ； Northwestern University（西北大学） 纠错

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

Journal ref SIGIR '25: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2025

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO

Francesco Pappone, Ruggero Marino Lazzaroni, Federico Califano, Niccolò Gentile, Roberto Marras

机构 * AI Sparks（AI火花） ； University of Graz（格拉茨大学） ； Foyer Group（Foyer集团） ； Onepix Academy（Onepix学院） 纠错

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

Overcoming classic challenges for artificial neural networks by providing incentives and practice

Kazuki Irie, Brenden M. Lake

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

Comments In press at Nature Machine Intelligence

Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance

Antoine Grosnit, Alexandre Maraval, Refinath S N, Zichao Zhao, James Doran, Giuseppe Paolo, Albert Thomas, Jonas Gonzalez, Abhineet Kumar, Khyati Khandelwal, Abdelhakim Benechehab, Hamza Cherkaoui, Youssef Attia El-Hili, Kun Shao, Jianye Hao, Jun Yao, Balázs Kégl, Haitham Bou-Ammar, Jun Wang

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

Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework

Zucheng Liang, Wenxin Wei, Kaijie Zhang, Hongyi Chen

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

From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks

Jacob Russin, Sam Whitman McGrath, Danielle J. Williams

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

Comments 19 pages (28 pages including references), 2 figures. Forthcoming in an edited volume on neuroscience and philosophy

Psychologically Enhanced AI Agents

Maciej Besta, Shriram Chandran, Robert Gerstenberger, Mathis Lindner, Marcin Chrapek, Sebastian Hermann Martschat, Taraneh Ghandi, Patrick Iff, Hubert Niewiadomski, Piotr Nyczyk, Jürgen Müller, Torsten Hoefler

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