大模型推理能力 - arXivDaily 专题

2507.08664 2025-07-14 cs.AI 70%

Introspection of Thought Helps AI Agents

Haoran Sun, Shaoning Zeng

机构 * Yangtze Delta Region Institute (Huzhou), University of Electronic and Science Technology of China（长江三角洲地区研究院（湖州），电子科技大学）； School of Information and Software Engineering, University of Electronic and Science Technology of China（信息与软件工程学院，电子科技大学）； Zhejiang Chuangjiekedong Ltd., Huzhou, Zhejiang, China（浙江创捷科技有限公司，湖州，浙江，中国）

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

2507.06838 2025-07-11 cs.CL cs.IR 70%

Shifting from Ranking to Set Selection for Retrieval Augmented Generation

Dahyun Lee, Yongrae Jo, Haeju Park, Moontae Lee

机构 * LG AI Research（LG人工智能研究）

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

Comments Accepted to ACL 2025 main (Oral Presentation)

2507.04708 2025-07-08 cs.CL 70%

Why We Feel What We Feel: Joint Detection of Emotions and Their Opinion Triggers in E-commerce

Arnav Attri, Anuj Attri, Pushpak Bhattacharyya, Suman Banerjee, Amey Patil, Muthusamy Chelliah, Nikesh Garera

机构 * Computer Science and Engineering, IIT Bombay, India（计算机科学与工程系，印度理工学院班加罗尔）； Flipkart, India（Flipkart，印度）

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

Comments 23 pages, 11 figures, 7 tables. Dataset and code will be made publicly available

2506.23408 2025-07-01 cs.LG cs.LO 70%

Do LLMs Dream of Discrete Algorithms?

Claudionor Coelho, Yanen Li, Philip Tee

机构 * Zscaler Inc（Zscaler公司）； ECE Department, Santa Clara University（圣克拉拉大学电子工程与计算机科学系）； Department of Informatics, University of Sussex（苏塞克斯大学信息学院）； The Beyond Center for Fundamental Science, Arizona State University（亚利桑那州立大学基础科学中心）

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

2408.06904 2025-06-23 cs.CL 70%

Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives

Zhihu Wang, Shiwan Zhao, Yu Wang, Heyuan Huang, Sitao Xie, Yubo Zhang, Jiaxin Shi, Zhixing Wang, Hongyan Li, Junchi Yan

机构 * Huawei Technologies Ltd.（华为技术有限公司）； Nankai University（南开大学）； Xi’an Jiaotong University（西安交通大学）； Shanghai Jiaotong University（上海交通大学）

专题命中复杂问题求解：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL

Comments ACL 2025 Findings; First three authors contributed equally

2506.12607 2025-06-17 cs.CL 70%

Towards Building General Purpose Embedding Models for Industry 4.0 Agents

Christodoulos Constantinides, Shuxin Lin, Dhaval Patel

机构 * IBM

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

2506.12527 2025-06-17 cs.CL 70%

Detection, Classification, and Mitigation of Gender Bias in Large Language Models

Xiaoqing Cheng, Hongying Zan, Lulu Kong, Jinwang Song, Min Peng

机构 * Zhengzhou University（郑州大学）； Wuhan University（武汉大学）

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

2506.04625 2025-06-06 cs.CL 70%

Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning

Zhiyuan Ma, Jiayu Liu, Xianzhen Luo, Zhenya Huang, Qingfu Zhu, Wanxiang Che

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学）； Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology（社会计算与交互机器人研究中心，哈尔滨工业大学）

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

Comments Accepted at the Research Track of KDD 2025

2506.04514 2025-06-06 cs.NI cs.AI 70%

BEAR: BGP Event Analysis and Reporting

Hanqing Li, Melania Fedeli, Vinay Kolar, Diego Klabjan

机构 * Engineering Sciences and Applied Mathematics Department（工程科学与应用数学系）； Amazon Web Services (AWS)（亚马逊网络服务（AWS））； Industrial Engineering and Management Sciences Department（工业工程与管理科学系）

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

2506.01538 2025-06-04 cs.RO cs.AI 70%

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation

Guobin Zhu, Rui Zhou, Wenkang Ji, Shiyu Zhao

机构 * School of Automation Science and Electrical Engineering, Beihang University（自动化科学与电气工程学院，北京航空航天大学）； WINDY Lab, Department of Artificial Intelligence, Westlake University（WINDY实验室，人工智能学院，西湖大学）

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

Comments Accepted by IEEE Robotics and Automation Letters

2506.00391 2025-06-03 cs.CL 70%

SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL

Ge Qu, Jinyang Li, Bowen Qin, Xiaolong Li, Nan Huo, Chenhao Ma, Reynold Cheng

机构 * The University of Hong Kong（香港大学）； BAAI（百度人工智能研究院）； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

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

Comments Accepted to ACL 2025 Main

2502.11404 2025-06-02 cs.CL 70%

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models

Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS（人工智能安全国家重点实验室，计算技术研究所，中国科学院）； University of Chinese Academy of Sciences（中国科学院大学）； Alibaba Group（阿里巴巴集团）

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

Comments Accepted to ACL 2025

2505.23242 2025-05-30 cs.CL 70%

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering

Jingxuan Wei, Nan Xu, Junnan Zhu, Yanni Hao, Gaowei Wu, Bihui Yu, Lei Wang

机构 * Beijing Wenge Technology Co., Ltd.（北京文格科技有限公司）； Shenyang Institute of Computing Technology, Chinese Academy of Sciences（沈阳计算技术研究所，中国科学院）； MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）； University of Chinese Academy of Sciences（中国科学院大学）

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

2505.03574 2025-05-07 cs.CR cs.AI 70%

LlamaFirewall: An open source guardrail system for building secure AI agents

Sahana Chennabasappa, Cyrus Nikolaidis, Daniel Song, David Molnar, Stephanie Ding, Shengye Wan, Spencer Whitman, Lauren Deason, Nicholas Doucette, Abraham Montilla, Alekhya Gampa, Beto de Paola, Dominik Gabi, James Crnkovich, Jean-Christophe Testud, Kat He, Rashnil Chaturvedi, Wu Zhou, Joshua Saxe

机构 * Meta

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

2504.14597 2025-04-22 cs.CL 70%

a1: Steep Test-time Scaling Law via Environment Augmented Generation

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Yuyao Ge, Jun Wan, Yurong Wu, Xueqi Cheng

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

2503.04104 2025-04-15 cs.CL 70%

LLMs Can Generate a Better Answer by Aggregating Their Own Responses

Zichong Li, Xinyu Feng, Yuheng Cai, Zixuan Zhang, Tianyi Liu, Chen Liang, Weizhu Chen, Haoyu Wang, Tuo Zhao

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

2407.06951 2025-04-04 cs.RO cs.LG 70%

RoboCAS: A Benchmark for Robotic Manipulation in Complex Object Arrangement Scenarios

Liming Zheng, Feng Yan, Fanfan Liu, Chengjian Feng, Zhuoliang Kang, Lin Ma

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

2504.00473 2025-04-02 cs.CL 70%

Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences

Xiangyang Liu, Junliang He, Xipeng Qiu

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

Comments Accepted by EMNLP 2024

2503.21602 2025-03-28 cs.AI 70%

GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise

Karime Maamari, Connor Landy, Amine Mhedhbi

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

2503.13856 2025-03-19 cs.AI 70%

MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation

Kai Chen, Xinfeng Li, Tianpei Yang, Hewei Wang, Wei Dong, Yang Gao

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

Comments 24 pages

2312.11242 2025-03-19 cs.CL 70%

MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL

Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li

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

Comments Accepted by COLING 2025 (Oral)

2501.11551 2025-03-13 cs.CL 70%

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

Jinyu Wang, Jingjing Fu, Rui Wang, Lei Song, Jiang Bian

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

Comments 38 pages, 18 figures, technique report

2503.01710 2025-03-04 cs.SD cs.AI eess.AS 70%

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Xinsheng Wang, Mingqi Jiang, Ziyang Ma, Ziyu Zhang, Songxiang Liu, Linqin Li, Zheng Liang, Qixi Zheng, Rui Wang, Xiaoqin Feng, Weizhen Bian, Zhen Ye, Sitong Cheng, Ruibin Yuan, Zhixian Zhao, Xinfa Zhu, Jiahao Pan, Liumeng Xue, Pengcheng Zhu, Yunlin Chen, Zhifei Li, Xie Chen, Lei Xie, Yike Guo, Wei Xue

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

Comments Submitted to ACL 2025

2503.01273 2025-03-04 cs.AI physics.flu-dyn 70%

OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFD

Yuxuan Chen, Long Zhang, Xu Zhu, Hua Zhou, Zhuyin Ren

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

Comments 26 pages,11 figures

2503.00902 2025-03-04 cs.CL 70%

Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction

Liping Liu, Chunhong Zhang, Likang Wu, Chuang Zhao, Zheng Hu, Ming He, Jianping Fan

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

Comments 23 pages, 5 figures, accepted by NAACL2025

2412.09605 2025-03-04 cs.CL 70%

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

Yiheng Xu, Dunjie Lu, Zhennan Shen, Junli Wang, Zekun Wang, Yuchen Mao, Caiming Xiong, Tao Yu

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

Comments ICLR2025 Spotlight https://agenttrek.github.io

2502.17888 2025-02-26 cs.CL 70%

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

Mingyan Wu, Zhenghao Liu, Yukun Yan, Xinze Li, Shi Yu, Zheni Zeng, Yu Gu, Ge Yu

专题命中复杂问题求解：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL

2502.07374 2025-02-19 cs.AI 70%

LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Dacheng Li, Shiyi Cao, Tyler Griggs, Shu Liu, Xiangxi Mo, Eric Tang, Sumanth Hegde, Kourosh Hakhamaneshi, Shishir G. Patil, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica

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

2312.16262 2025-02-19 cs.IR cs.AI 70%

Adaptive In-Context Learning with Large Language Models for Bundle Generation

Zhu Sun, Kaidong Feng, Jie Yang, Xinghua Qu, Hui Fang, Yew-Soon Ong, Wenyuan Liu

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

Comments Accepted by SIGIR 2024

Journal ref The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2024

2502.11250 2025-02-18 cs.CL 70%

Uncertainty-Aware Step-wise Verification with Generative Reward Models

Zihuiwen Ye, Luckeciano Carvalho Melo, Younesse Kaddar, Phil Blunsom, Sam Staton, Yarin Gal

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

1. 复杂问题求解 5001 篇

Introspection of Thought Helps AI Agents

Shifting from Ranking to Set Selection for Retrieval Augmented Generation

Why We Feel What We Feel: Joint Detection of Emotions and Their Opinion Triggers in E-commerce

Do LLMs Dream of Discrete Algorithms?

Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives

Towards Building General Purpose Embedding Models for Industry 4.0 Agents

Detection, Classification, and Mitigation of Gender Bias in Large Language Models

Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning

BEAR: BGP Event Analysis and Reporting

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation

SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering

LlamaFirewall: An open source guardrail system for building secure AI agents

a1: Steep Test-time Scaling Law via Environment Augmented Generation

LLMs Can Generate a Better Answer by Aggregating Their Own Responses

RoboCAS: A Benchmark for Robotic Manipulation in Complex Object Arrangement Scenarios

Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences

GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise

MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation

MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFD

Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Adaptive In-Context Learning with Large Language Models for Bundle Generation

Uncertainty-Aware Step-wise Verification with Generative Reward Models