RAG / 检索增强生成 - arXivDaily 专题

2602.15859 2026-02-19 cs.CL 83%

From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants

从语音记录到AI代理：知识提取、RAG整合及对话式AI助手的鲁棒评估

Krittin Pachtrachai, Petmongkon Pornpichitsuwan, Wachiravit Modecrua, Touchapon Kraisingkorn

机构 * Amity Research and Application Center (ARAC)（阿米蒂研究与应用中心）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结本文提出了一种端到端框架，通过历史通话记录构建和评估对话式AI助手，利用知识提取和RAG整合提升事实准确性和鲁棒性。

Comments 9 pages, 2 figures, 1 table

2509.21875 2026-02-04 cs.CL 83%

LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals

LUMINA：通过上下文-知识信号检测RAG系统中的幻觉

Samuel Yeh, Sharon Li, Tanwi Mallick

机构 * Department of Computer Science, University of Wisconsin-Madison（威斯康星大学麦迪逊分校计算机科学系）； Argonne National Laboratory（阿贡国家实验室）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结 LUMINA通过上下文-知识信号检测RAG系统中的幻觉，利用分布距离和token演变测量，实现高准确率和实用性。

Comments ICLR 2026

2601.18267 2026-01-27 cs.IR 83%

Orchestrating Specialized Agents for Trustworthy Enterprise RAG

协调专用代理以实现可信的企业RAG

Xincheng You, Qi Sun, Neha Bora, Huayi Li, Shubham Goel, Kang Li, Sean Culatana

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.IR

AI总结 ADORE通过结构化记忆库和迭代协调机制，提升企业RAG在高风险决策中的可追溯性和证据完整性。

2601.14949 2026-01-27 cs.IR 83%

What Should I Cite? A RAG Benchmark for Academic Citation Prediction

我应该引用什么？一个用于学术引用预测的RAG基准

Leqi Zheng, Jiajun Zhang, Canzhi Chen, Chaokun Wang, Hongwei Li, Yuying Li, Yaoxin Mao, Shannan Yan, Zixin Song, Zhiyuan Feng, Zhaolu Kang, Zirong Chen, Hang Zhang, Qiang Liu, Liang Wang, Ziyang Liu

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.IR

AI总结 CiteRAG提出一个用于学术引用预测的RAG基准，通过多层次检索策略和生成器，评估大型语言模型在引用预测中的性能。

Journal ref WWW 2026

2511.09122 2026-01-19 cs.SE cs.AI 83%

Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code Generation

面向供应商的工业代理：增强型LLM用于安全本地PLC代码生成

Joschka Kersting, Michael Rummel, Gesa Benndorf

机构 * Centre for Machine Learning（机器学习中心）； Fraunhofer IOSB-INA（弗劳恩霍夫IOSB-INA研究所）； FA-EDC ； Mitsubishi Electric Europe（三菱电机欧洲）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

AI总结本文提出了一种基于RAG增强的LLM方法，用于在低数据域中安全生成本地PLC代码，通过提示工程和定向检索提升代码生成质量。

Comments ICIT2026

2506.12071 2026-01-19 cs.IR 83%

T$^2$-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation

T$^2$-RAGBench：用于评估检索增强生成的文本与表格基准

Jan Strich, Enes Kutay Isgorur, Maximilian Trescher, Chris Biemann, Martin Semmann

专题命中 RAG评测：retrieval-augmented generation(title)；retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.IR

AI总结 T$^2$-RAGBench是一个用于评估检索增强生成在文本和表格数据上性能的基准，通过上下文无关的问题测试RAG方法，发现Hybrid BM25在处理此类数据时表现最佳，但仍然对最先进的模型构成挑战。

Comments Accepted to EACL 2026

2509.24253 2026-01-14 cs.CL 83%

MRAG-Suite: A Diagnostic Evaluation Platform for Visual Retrieval-Augmented Generation

MRAG-Suite：一个用于视觉检索增强生成的诊断评估平台

Yuelyu Ji, Wuwei Lan, Patrick NG

机构 * University of Pittsburgh（匹兹堡大学）

专题命中 RAG评测：retrieval-augmented generation(title,abstract)；RAG(abstract)；分类 cs.CL

AI总结 MRAG-Suite通过引入难度和歧义过滤策略及诊断工具MM-RAGChecker，系统评估视觉检索增强生成的性能与常见幻觉问题。

2601.01785 2026-01-06 cs.IR cs.LG 83%

SRAS: A Lightweight Reinforcement Learning-based Document Selector for Edge-Native RAG Pipelines

SRAS：一种基于强化学习的轻量级文档选择器用于边缘原生RAG流水线

Rajiv Chaitanya Muttur

机构 * Dayananda Sagar College of Engineering, Bangalore, India（达扬达萨加尔工程学院，班加罗尔，印度）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.IR

AI总结 SRAS通过强化学习训练出轻量级文档选择器，适用于边缘原生RAG流水线，实现低延迟和高生成质量。

Comments Presented at ICEdge 2025; nominated for Best Paper Award

2601.01341 2026-01-06 cs.CL 83%

Reasoning Over Recall: Evaluating the Efficacy of Generalist Architectures vs. Specialized Fine-Tunes in RAG-Based Mental Health Dialogue Systems

基于回忆的推理：评估基于RAG的心理健康对话系统中通用架构与专门微调的有效性

Md Abdullah Al Kafi, Raka Moni, Sumit Kumar Banshal

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结本文通过比较通用推理模型与领域特定微调模型，发现通用模型在同理心和上下文理解方面表现更优，表明强大的推理能力比专门训练更能提升心理健康对话系统的效果。

2601.00254 2026-01-05 cs.SE cs.AI 83%

An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems

基于大型语言模型的代码漏洞检测方法实证评估：RAG、SFT和双智能体系统

Md Hasan Saju, Maher Muhtadi, Akramul Azim

机构 * Department of Electrical, Computer, and Software Engineering（电气、计算机与软件工程系）； Ontario Tech University（安大略技术大学）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

AI总结本文通过实证评估，比较了RAG、SFT和双智能体系统在代码漏洞检测中的有效性，发现RAG在准确率和F1分数上表现最佳，SFT和双智能体系统也展示了良好的性能，证明了领域专业知识对LLM在实际漏洞检测中的重要性。

Journal ref https://conf.researchr.org/home/cascon-2025

2412.04235 2026-01-01 cs.CL 83%

Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots

通过RAG和NMISS解决意大利医疗LLM聊天机器人中的幻觉

Maria Paola Priola

机构 * Department of Economics and Business, University of Cagliari（经济与商业系，卡利亚里大学）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结本文通过RAG和NMISS方法有效缓解和检测LLM中的幻觉问题，验证了GPT-4和NMISS对提升医疗领域LLM性能的显著效果。

2504.02800 2025-12-23 cs.CL 83%

Survey and Experiments on Mental Disorder Detection via Social Media: From Large Language Models and RAG to Agents

面向社交媒体的抑郁症检测综述与实验：从大型语言模型和RAG到代理

Zhuohan Ge, Darian Li, Yubo Wang, Nicole Hu, Xinyi Zhu, Haoyang Li, Xin Zhang, Mingtao Zhang, Shihao Qi, Yuming Xu, Han Shi, Chen Jason Zhang, Qing Li

机构 * The Hong Kong Polytechnic University（香港理工大学）； The Hong Kong University of Science and Technology（香港科学与技术大学）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结本文综述并实验了基于社交媒体的抑郁症检测方法，探讨了LLM、RAG和代理系统在提升检测可靠性与推理能力中的应用。

Comments 20 pages, 10 figures. This is an extension of ICDEW 2025

2505.14069 2025-12-09 cs.IR 83%

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

过程奖励与结果奖励：哪种对代理RAG强化学习更有效

Wenlin Zhang, Xiangyang Li, Kuicai Dong, Yichao Wang, Pengyue Jia, Xiaopeng Li, Yingyi Zhang, Derong Xu, Zhaocheng Du, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.IR

AI总结 ReasonRAG通过过程级奖励提升代理RAG强化学习性能，以更高效训练和更少数据实现更优结果

2511.12003 2025-12-02 cs.AI 83%

Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning

看而思：通过强化学习统一推理与视觉证据归因以实现可验证文档RAG

Shuochen Liu, Pengfei Luo, Chao Zhang, Yuhao Chen, Haotian Zhang, Qi Liu, Xin Kou, Tong Xu, Enhong Chen

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

AI总结通过强化学习统一推理与视觉证据归因，提升多模态问答的可验证性和准确性。

Comments Poster of AAAI'2026

2506.05925 2025-11-18 cs.CY cs.AI 83%

Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAG

Zarreen Reza, Alexander Mazur, Michael T. Dugdale, Robin Ray-Chaudhuri

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

2511.10523 2025-11-14 cs.CL 83%

Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG

Egor Pakhomov, Erik Nijkamp, Caiming Xiong

机构 * Salesforce AI Research（Salesforce人工智能研究）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

2511.09545 2025-11-13 cs.IR 83%

Practical RAG Evaluation: A Rarity-Aware Set-Based Metric and Cost-Latency-Quality Trade-offs

Etienne Dallaire

专题命中 RAG评测：RAG(title,abstract)；dense retrieval(abstract)；分类 cs.IR

2511.06738 2025-11-11 cs.CL 83%

Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights

Hyunjae Kim, Jiwoong Sohn, Aidan Gilson, Nicholas Cochran-Caggiano, Serina Applebaum, Heeju Jin, Seihee Park, Yujin Park, Jiyeong Park, Seoyoung Choi, Brittany Alexandra Herrera Contreras, Thomas Huang, Jaehoon Yun, Ethan F. Wei, Roy Jiang, Leah Colucci, Eric Lai, Amisha Dave, Tuo Guo, Maxwell B. Singer, Yonghoe Koo, Ron A. Adelman, James Zou, Andrew Taylor, Arman Cohan, Hua Xu, Qingyu Chen

机构 * Yale School of Medicine（耶鲁医学院）； Yale University（耶鲁大学）； ETH Zurich（苏黎世联邦理工学院）； Harvard Medical School（哈佛医学院）； Geisel School of Medicine at Dartmouth（达特茅斯大学盖塞医学院）； Seoul National University College of Medicine（首尔国立大学医学院）； Hanyang University College of Medicine（翰林大学医学院）； PA Leadership Charter School（宾夕法尼亚州西切斯特市领导学校）

专题命中 RAG评测：retrieval-augmented generation(title,abstract)；RAG(abstract)；分类 cs.CL

Comments 34 pages, 6 figures

2511.06212 2025-11-11 cs.CR cs.AI 83%

RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework

Seif Ikbarieh, Kshitiz Aryal, Maanak Gupta

机构 * Department of Computer Science（计算机科学系）； Tennessee Tech University（田纳西科技大学）； School of Interdisciplinary Informatics（跨学科信息学学院）； University of Nebraska Omaha（内布拉斯加大学奥马哈分校）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

2509.09360 2025-11-10 cs.CL 83%

MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems

Channdeth Sok, David Luz, Yacine Haddam

机构 * Forvia Paris Tech Center, GIT, Immeuble Lumière, 40 avenue des Terroirs de France, 75012 Paris, France（巴黎Forvia技术中心，GIT，Lumière大厦，法国巴黎75012）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

Comments Identity-Aware AI workshop at 28th European Conference on Artificial Intelligence, October 25, 2025, Bologna, Italy

2412.15189 2025-10-30 cs.CL cs.CY 83%

Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking

Daniel Russo, Stefano Menini, Jacopo Staiano, Marco Guerini

机构 * Fondazione Bruno Kessler（布罗诺·凯塞勒基金会）； University of Trento（特伦托大学）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

Comments Code and data at https://github.com/drusso98/face-the-facts - Accepted for publication at INLG 2025

2506.00789 2025-10-29 cs.CL 83%

RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems

Yixiao Zeng, Tianyu Cao, Danqing Wang, Xinran Zhao, Zimeng Qiu, Morteza Ziyadi, Tongshuang Wu, Lei Li

机构 * Carnegie Mellon University Language Technologies Institute（卡内基梅隆大学语言技术研究所）； Amazon（亚马逊）

专题命中 RAG评测：retrieval-augmented generation(title,abstract)；RAG(abstract)；分类 cs.CL

2507.04055 2025-10-28 cs.CR cs.AI cs.SE 83%

Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG

Yufan Chen, Daoyuan Wu, Juantao Zhong, Zicheng Zhang, Debin Gao, Shuai Wang, Yingjiu Li, Ning Liu, Jiachi Chen, Rocky K. C. Chang

机构 * University of Oregon（俄勒冈大学）； City University of Hong Kong（香港城市大学）； Sun Yat-sen University（中山大学）； Calvin University（加州学院）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

Comments This is a technical report from Lingnan University, Hong Kong. Code is available at https://github.com/AIS2Lab/MalwareGPT

2510.20878 2025-10-27 cs.LG cs.AI 83%

HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement

Danying Ge, Jianhua Gao, Yixue Yang, Weixing Ji

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

Comments 13 pages,16 figures,2 tables

2510.18455 2025-10-22 cs.CL 83%

ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks

Liyang He, Yuren Zhang, Ziwei Zhu, Zhenghui Li, Shiwei Tong

专题命中 RAG评测：RAG(title,abstract)；retrieval augmented generation(abstract)；分类 cs.CL

2510.17874 2025-10-22 cs.SE cs.AI 83%

Repairing Tool Calls Using Post-tool Execution Reflection and RAG

Jason Tsay, Zidane Wright, Gaodan Fang, Kiran Kate, Saurabh Jha, Yara Rizk

机构 * IBM Research（IBM研究院）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

2510.12316 2025-10-15 cs.CL 83%

Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation

Greta Damo, Elena Cabrio, Serena Villata

机构 * Université Côte d’Azur, CNRS, Inria, I3S, France（法国大学-科蒂-阿祖尔大学、国家科学研究中心、法国国家信息与自动化研究所、I3S研究所）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

2510.10824 2025-10-14 cs.SE cs.AI 83%

Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration

Mohanakrishnan Hariharan, Satish Arvapalli, Seshu Barma, Evangeline Sheela

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

2502.11400 2025-10-06 cs.CL 83%

On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs

Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Liwei Chen, Kun Xu, Huawei Shen, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（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）； Tongyi Lab, Alibaba Group（通义实验室，阿里巴巴集团）； Institute of Computing Technology（计算技术研究所）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

Comments Accepted at SIGIR-AP 2025

2510.00001 2025-10-02 cs.LG cs.AI cs.SE 83%

Methodological Framework for Quantifying Semantic Test Coverage in RAG Systems

Noah Broestl, Adel Nasser Abdalla, Rajprakash Bale, Hersh Gupta, Max Struever

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

Comments 7 pages, 3 figures, 1 table, 1 algo

1. RAG评测 1223 篇

From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants

LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals

Orchestrating Specialized Agents for Trustworthy Enterprise RAG

What Should I Cite? A RAG Benchmark for Academic Citation Prediction

Vendor-Aware Industrial Agents: RAG-Enhanced LLMs for Secure On-Premise PLC Code Generation

T$^2$-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation

MRAG-Suite: A Diagnostic Evaluation Platform for Visual Retrieval-Augmented Generation

SRAS: A Lightweight Reinforcement Learning-based Document Selector for Edge-Native RAG Pipelines

Reasoning Over Recall: Evaluating the Efficacy of Generalist Architectures vs. Specialized Fine-Tunes in RAG-Based Mental Health Dialogue Systems

An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems

Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots

Survey and Experiments on Mental Disorder Detection via Social Media: From Large Language Models and RAG to Agents

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning

Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAG

Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG

Practical RAG Evaluation: A Rarity-Aware Set-Based Metric and Cost-Latency-Quality Trade-offs

Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights

RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework

MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems

Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking

RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems

Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG

HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement

ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks

Repairing Tool Calls Using Post-tool Execution Reflection and RAG

Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation

Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration

On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs

Methodological Framework for Quantifying Semantic Test Coverage in RAG Systems