大模型推理能力

Generative Reasoning Recommendation via LLMs

Minjie Hong, Zetong Zhou, Zirun Guo, Ziang Zhang, Ruofan Hu, Weinan Gan, Jieming Zhu, Zhou Zhao

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

MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?

Kai Yan, Zhan Ling, Kang Liu, Yifan Yang, Ting-Han Fan, Lingfeng Shen, Zhengyin Du, Jiecao Chen

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

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

Comments 39 pages, 11 figures. The paper is accepted at NeurIPS 2025 Datasets & Benchmarks Track, and the latest version adds modifications in camera-ready

What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation

Heejin Do, Jaehui Hwang, Dongyoon Han, Seong Joon Oh, Sangdoo Yun

机构 * ETH Zürich, ETH AI Center（苏黎世联邦理工学院，ETH人工智能中心） ； NAVER AI Lab（NAVER人工智能实验室） ； University of Tübingen（图宾根大学） 纠错

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

Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning

Wenyi Xiao, Leilei Gan

机构 * Zhejiang University（浙江大学） 纠错

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

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

Yu Fu, Zefan Cai, Abedelkadir Asi, Wayne Xiong, Yue Dong, Wen Xiao

机构 * University of California, Riverside（加州大学河滨分校） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Microsoft（微软公司） 纠错

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

Comments Accepted to ICLR2025

Benchmarking Reasoning Reliability in Artificial Intelligence Models for Energy-System Analysis

Eliseo Curcio

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

Multimedia-Aware Question Answering: A Review of Retrieval and Cross-Modal Reasoning Architectures

Rahul Raja, Arpita Vats

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Boston University（波士顿大学） 纠错

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

Comments In Proceedings of the 2nd ACM Workshop in AI-powered Question and Answering Systems (AIQAM '25), October 27-28, 2025, Dublin, Ireland. ACM, New York, NY, USA, 8 pages. https://doi.org/10.1145/3746274.3760393

RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration

Xiuyuan Chen, Jian Zhao, Yuchen Yuan, Tianle Zhang, Huilin Zhou, Zheng Zhu, Ping Hu, Linghe Kong, Chi Zhang, Weiran Huang, Xuelong Li

机构 * Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信） ； School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； University of Science and Technology of China（中国科学技术大学） ； GigaAI ； School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院） 纠错

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

CLEVER: A Curated Benchmark for Formally Verified Code Generation

Amitayush Thakur, Jasper Lee, George Tsoukalas, Meghana Sistla, Matthew Zhao, Stefan Zetzsche, Greg Durrett, Yisong Yue, Swarat Chaudhuri

机构 * UT Austin（得克萨斯大学） ； Amazon（亚马逊） ； Caltech（加州理工学院） 纠错

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

Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants

Lixiong Qin, Shilong Ou, Miaoxuan Zhang, Jiangning Wei, Yuhang Zhang, Xiaoshuai Song, Yuchen Liu, Mei Wang, Weiran Xu

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Beijing Normal University（北京师范大学） 纠错

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

Comments 50 pages, 14 figures, 42 tables. NeurIPS 2025 Datasets and Benchmarks Track

Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities

Nishant Balepur, Dang Nguyen, Dayeon Ki

机构 * University of Maryland（马里兰大学） 纠错

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

Comments Accepted as a Spotlight paper at the EMNLP 2025 Wordplay Workshop

Collateral Damage Assessment Model for AI System Target Engagement in Military Operations

Clara Maathuis, Kasper Cools

机构 * Open University of the Netherlands（荷兰开放大学） ； Royal Military Academy, Belgium（比利时皇家军事学院） ； Vrije Universiteit Brussel, Belgium（比利时自由大学） 纠错

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

Comments Accepted at MILCOM 2025 WS07

There is No "apple" in Timeseries: Rethinking TSFM through the Lens of Invariance

Arian Prabowo, Flora D. Salim

机构 * School of Computer Science and Engineering（计算机科学与工程学院） ； University of New South Wales（新南威尔士大学） 纠错

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

"You Are Rejected!": An Empirical Study of Large Language Models Taking Hiring Evaluations

Dingjie Fu, Dianxing Shi

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

Comments Technical Report, 14 pages, 8 figures

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models

Yeonjun In, Wonjoong Kim, Kanghoon Yoon, Sungchul Kim, Mehrab Tanjim, Sangwu Park, Kibum Kim, Chanyoung Park

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

Comments EMNLP 2025 Findings

SpeechAgent: An End-to-End Mobile Infrastructure for Speech Impairment Assistance

Haowei Lou, Chengkai Huang, Hye-young Paik, Yongquan Hu, Aaron Quigley, Wen Hu, Lina Yao

机构 * University of New South Wales（新南威尔士大学） ； Macquarie University（麦考瑞大学） ； National University of Singapore（国立新加坡大学） ； CSIRO's Data61（澳大利亚联邦科学与工业研究组织Data61部门） 纠错

专题命中 推理评测 ：reasoning(abstract)

REOBench: Benchmarking Robustness of Earth Observation Foundation Models

Xiang Li, Yong Tao, Siyuan Zhang, Siwei Liu, Zhitong Xiong, Chunbo Luo, Lu Liu, Mykola Pechenizkiy, Xiao Xiang Zhu, Tianjin Huang

机构 * University of Bristol, UK（英国布里斯托大学） ； University of Exeter, UK（英国埃克塞特大学） ； South China Normal University, China（华南师范大学） ； The University of Aberdeen, UK（英国阿伯丁大学） ； Technical University of Munich, Germany（慕尼黑技术大学） ； Eindhoven University of Technology, NL（埃因霍温理工大学） 纠错

专题命中 推理评测 ：planning(abstract)

Comments Accepted to NeruIPS 2025 D&B Track