大模型推理能力

Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models

Tan-Hanh Pham, Chris Ngo

机构 * Harvard Medical School, Harvard University（哈佛医学院、哈佛大学） ； Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital（阿提尼乌拉A.马丁努斯生物医学成像中心、麻省总医院） ； Knovel Engineering Lab, Singapore（Knovel工程实验室、新加坡） 纠错

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

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing

Xinnan Dai, Chung-Hsiang Lo, Kai Guo, Shenglai Zeng, Dongsheng Luo, Jiliang Tang

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

Comments Accepted by the Workshop on Efficient Reasoning, Neurips 2025

PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning

Xueliang Zhao, Wei Wu, Jian Guan, Zhuocheng Gong, Lingpeng Kong

机构 * The University of Hong Kong（香港大学） 纠错

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

Comments Preprint

The Conductor and the Engine: A Path Towards Co-Designed Reasoning

Yuanxin Wang, Pawel Filipczuk, Anisha Garg, Amaan Dhada, Mohammad Hassanpour, David Bick, Ganesh Venkatesh

机构 * Applied AI Research, Cerebras（应用人工智能研究，Cerebras） 纠错

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

How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?

Sohee Yang, Sang-Woo Lee, Nora Kassner, Daniela Gottesman, Sebastian Riedel, Mor Geva

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

Comments Findings of EMNLP 2025

Reverse Engineering User Stories from Code using Large Language Models

Mohamed Ouf, Haoyu Li, Michael Zhang, Mariam Guizani

机构 * Queen's University（皇后大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

One Filters All: A Generalist Filter for State Estimation

Shiqi Liu, Wenhan Cao, Chang Liu, Zeyu He, Tianyi Zhang, Shengbo Eben Li

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院） ； College of Engineering, Peking University（北京大学工程学院） ； College of AI, Tsinghua University（清华大学人工智能学院） 纠错

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

Comments NeurIPS 2025

GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models

Dylan Hutson, Daniel Vennemeyer, Aneesh Deshmukh, Justin Zhan, Tianyu Jiang

机构 * University of Cincinnati（辛辛那提大学） 纠错

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

Comments EMNLP 2025, 17 pages, 2 figures

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation

Huizhen Shu, Xuying Li, Zhuo Li

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

Comments 9-page NeurIPS 2025 preprint including 3 figures and 1 table, with additional appendix material. Prepared using the NeurIPS 2025 preprint template and compiled with pdfLaTeX. All references are included via the provided .bbl file. Figures are in PDF format. No external supplementary files. All necessary style files and images are included

Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling

Youpeng Zhao, Jinpeng LV, Di Wu, Jun Wang, Christopher Gooley

机构 * University of Central Florida（中央佛罗里达大学） ； Microsoft Research（微软研究院） 纠错

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

Multimodal Language Models with Modality-Specific Experts for Financial Forecasting from Interleaved Sequences of Text and Time Series

Ross Koval, Nicholas Andrews, Xifeng Yan

机构 * University of California, Santa Barbara（加州大学圣巴巴拉分校） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

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

Comments Preprint

How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment

Julie Jung, Max Lu, Sina Chole Benker, Dogus Darici

机构 * Harvard Graduate School of Education（哈佛教育研究生院） ； Munster University（穆恩斯特大学） ； Institute of Anatomy and Neurobiology, University of Münster（解剖与神经生物学研究所，穆恩斯特大学） 纠错

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

Comments 9 pages, 4 figures, accepted at NCME AIME 2025

Long Video Understanding with Learnable Retrieval in Video-Language Models

Jiaqi Xu, Cuiling Lan, Wenxuan Xie, Xuejin Chen, Yan Lu

机构 * School of Information Science and Technology, University of Science and Technology of China（信息科学与技术学院，中国科学技术大学） ； Microsoft Research Asia（微软亚洲研究院） 纠错

专题命中 其他推理 ：reasoning(abstract)

Comments Accepted by IEEE Transactions on Multimedia (TMM)