大模型推理能力

Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering

Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, 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(title,abstract)；分类 cs.CL

Comments ACL 2025 Findings

KnowPath: Knowledge-enhanced Reasoning via LLM-generated Inference Paths over Knowledge Graphs

Qi Zhao, Hongyu Yang, Qi Song, Xinwei Yao, Xiangyang Li

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

RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

Mingrui Wu, Lu Wang, Pu Zhao, Fangkai Yang, Jianjin Zhang, Jianfeng Liu, Yuefeng Zhan, Weihao Han, Hao Sun, Jiayi Ji, Xiaoshuai Sun, Qingwei Lin, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（多媒体可信感知与高效计算重点实验室，教育部，厦门大学） ； Microsoft（微软） 纠错

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

Comments Code is available at: https://github.com/microsoft/DKI_LLM/tree/main/RePrompt

Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging

Han Wu, Yuxuan Yao, Shuqi Liu, Zehua Liu, Xiaojin Fu, Xiongwei Han, Xing Li, Hui-Ling Zhen, Tao Zhong, Mingxuan Yuan

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

Comments Technical report

CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs

Guoheng Sun, Ziyao Wang, Bowei Tian, Meng Liu, Zheyu Shen, Shwai He, Yexiao He, Wanghao Ye, Yiting Wang, Ang Li

机构 * University of Maryland, College Park（马里兰大学 College Park 分校） 纠错

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

LLMSR@XLLM25: An Empirical Study of LLM for Structural Reasoning

Xinye Li, Mingqi Wan, Dianbo Sui

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

Disentangling Memory and Reasoning Ability in Large Language Models

Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, Yongfeng Zhang

机构 * Rutgers University（罗格斯大学） ； The Ohio State University（俄亥俄州立大学） ； University of California, Santa Barbara（加州大学圣巴巴拉分校） 纠错

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

Comments Accepted by ACL 2025

Boosting Neural Language Inference via Cascaded Interactive Reasoning

Min Li, Chun Yuan

机构 * Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院） 纠错

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

A Hashgraph-Inspired Consensus Mechanism for Reliable Multi-Model Reasoning

Kolawole E. Ogunsina, Morayo A. Ogunsina

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

Comments 15 pages

A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs

Mohit Vaishnav, Tanel Tammet

机构 * Applied Artificial Intelligence Group, Tallinn University of Technology, Estonia（塔林技术大学应用人工智能组） ； Kimova AI, Tallinn, Estonia（Kimova AI） 纠错

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

Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning

Joykirat Singh, Raghav Magazine, Yash Pandya, Akshay Nambi

机构 * Microsoft Research（微软研究院） 纠错

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

MINERVA: Evaluating Complex Video Reasoning

Arsha Nagrani, Sachit Menon, Ahmet Iscen, Shyamal Buch, Ramin Mehran, Nilpa Jha, Anja Hauth, Yukun Zhu, Carl Vondrick, Mikhail Sirotenko, Cordelia Schmid, Tobias Weyand

机构 * Google DeepMind（谷歌DeepMind） ； Columbia University（哥伦比亚大学） 纠错

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

Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning

Isadora White, Kolby Nottingham, Ayush Maniar, Max Robinson, Hansen Lillemark, Mehul Maheshwari, Lianhui Qin, Prithviraj Ammanabrolu

机构 * University of California, San Diego（加州大学圣地亚哥分校） ； Latitude Games ； Emergent Garden 纠错

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

Comments 9 pages of main paper with 6 main figures, overall 28 pages

OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery

Vignesh Prabhakar, Md Amirul Islam, Adam Atanas, Yao-Ting Wang, Joah Han, Aastha Jhunjhunwala, Rucha Apte, Robert Clark, Kang Xu, Zihan Wang, Kai Liu

机构 * SES AI（SES人工智能公司） ； NVIDIA（英伟达公司） 纠错

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

Self-Correction Makes LLMs Better Parsers

Ziyan Zhang, Yang Hou, Chen Gong, Zhenghua Li

机构 * School of Computer Science and Technology, Soochow University（计算机科学与技术学院，苏州大学） 纠错

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

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning

Jianing Wang, Jin Jiang, Yang Liu, Mengdi Zhang, Xunliang Cai

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

Assessing Judging Bias in Large Reasoning Models: An Empirical Study

Qian Wang, Zhanzhi Lou, Zhenheng Tang, Nuo Chen, Xuandong Zhao, Wenxuan Zhang, Dawn Song, Bingsheng He

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

DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs

Masoud Hashemi, Oluwanifemi Bamgbose, Sathwik Tejaswi Madhusudhan, Jishnu Sethumadhavan Nair, Aman Tiwari, Vikas Yadav

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

Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models

Yuxiang Lin, Jingdong Sun, Zhi-Qi Cheng, Jue Wang, Haomin Liang, Zebang Cheng, Yifei Dong, Jun-Yan He, Xiaojiang Peng, Xian-Sheng Hua

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

Comments Accepted at CVPR Workshop NEXD 2025. 21 pages, Project: https://github.com/Lum1104/EIBench

SaRO: Enhancing LLM Safety through Reasoning-based Alignment

Yutao Mou, Yuxiao Luo, Shikun Zhang, Wei Ye

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

Mixed Signals: Decoding VLMs' Reasoning and Underlying Bias in Vision-Language Conflict

Pouya Pezeshkpour, Moin Aminnaseri, Estevam Hruschka

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

L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution

Simeng Sun, Cheng-Ping Hsieh, Faisal Ladhak, Erik Arakelyan, Santiago Akle Serano, Boris Ginsburg

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

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level

Andong Deng, Tongjia Chen, Shoubin Yu, Taojiannan Yang, Lincoln Spencer, Yapeng Tian, Ajmal Saeed Mian, Mohit Bansal, Chen Chen

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

Comments CVPR 2025

LLM for Complex Reasoning Task: An Exploratory Study in Fermi Problems

Zishuo Liu, Carlos Rabat Villarreal, Mostafa Rahgouy, Amit Das, Zheng Zhang, Chang Ren, Dongji Feng

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

Comments 7 pages,7 tables, 5 figures

Teaching LLMs Music Theory with In-Context Learning and Chain-of-Thought Prompting: Pedagogical Strategies for Machines

Liam Pond, Ichiro Fujinaga

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

Comments 11 pages, 4 figures, 3 tables. Published in Volume 1 of the Proceedings of the 17th International Conference on Computer Supported Music Education (CSME 2025). Presented on 3 April 2025 in Porto, Portugal

Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models

Mario Sanz-Guerrero, Katharina von der Wense

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

Comments Accepted to the 6th Workshop on Insights from Negative Results in NLP at NAACL 2025

StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs

Hailin Chen, Fangkai Jiao, Mathieu Ravaut, Nawshad Farruque, Xuan Phi Nguyen, Chengwei Qin, Manan Dey, Bosheng Ding, Caiming Xiong, Shafiq Joty, Yingbo Zhou

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

Neutralizing Bias in LLM Reasoning using Entailment Graphs

Liang Cheng, Tianyi Li, Zhaowei Wang, Tianyang Liu, Mark Steedman

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

Comments 17 pages, 7 figures

Thinking Machines: A Survey of LLM based Reasoning Strategies

Dibyanayan Bandyopadhyay, Soham Bhattacharjee, Asif Ekbal

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

Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning

Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Wenjie Zhang

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

Comments Accepted by The Web Conference 2025 (WWW, 2025)