RAG / 检索增强生成

Annotation-Free Reinforcement Learning Query Rewriting via Verifiable Search Reward

无需标注的强化学习查询重写通过可验证的搜索奖励

Sungguk Cha, DongWook Kim, Taeseung Hahn, Mintae Kim, Youngsub Han, Byoung-Ki Jeon

机构 * LG Uplus（LG 通信） 纠错

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

AI总结 RL-QR通过可验证的搜索奖励实现无需标注的查询重写，显著提升检索性能，适用于多种模态和索引领域。

Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics

解析深度搜索：基于无提示多跳问题和因子化指标的全面评估

Maojia Song, Renhang Liu, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou, Dorien Herremans, Soujanya Poria

机构 * Singapore University of Technology and Design（新加坡科技设计大学） ； Nanyang Technological University（南洋理工大学） ； Tongyi Lab, Alibaba Group（阿里云实验室） 纠错

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

AI总结 本文提出WebDetective基准测试，通过无提示多跳问题和因子化指标，揭示深度搜索中模型在知识利用和拒绝行为上的系统性弱点，并开发EvidenceLoop工作流程以改进自主推理能力。

AI Application in Anti-Money Laundering for Sustainable and Transparent Financial Systems

人工智能在构建可持续和透明金融系统中的反洗钱应用

Chuanhao Nie, Yunbo Liu, Chao Wang

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

AI总结 本文提出利用人工智能技术提升反洗钱流程的效率和透明度，通过整合图检索增强生成模型，优化KYC流程以支持可持续金融发展。

A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent (Static-DRA)

一种基于层次树的创建可配置和静态深度研究代理（静态-DRA）的方法

Saurav Prateek

机构 * Saurav Prateek（独立研究者） 纠错

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

AI总结 本文提出静态-DRA，通过深度和广度参数实现可配置的深度研究代理，提升多轮复杂研究任务的处理能力。

Comments 16 pages, 6 figures, 4 tables. Code available at: https://github.com/SauravP97/Static-Deep-Research

Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability

让大语言模型效率普及：从超大规模优化到通用部署

Hen-Hsen Huang

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

AI总结 本文提出通过改进LLM的效率方法，使其在有限资源和专业知识下仍能有效运作，以实现更广泛的部署和公平性。

Comments 8 pages, accepted as a Blue Sky Talk in AAAI 2026

KRAL: Knowledge and Reasoning Augmented Learning for LLM-assisted Clinical Antimicrobial Therapy

KRAL: 用于LLM辅助临床抗菌治疗的知识与推理增强学习

Zhe Li, Yehan Qiu, Yujie Chen, Xiang Zhou

机构 * Information Center, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital（信息中心、复杂严重罕见疾病国家重点实验室、北京友谊医院） ； Department of Critical Care Medicine, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Peking Union Medical College and Chinese Academy of Medical Sciences（重症医学科、复杂严重罕见疾病国家重点实验室、北京友谊医院、北京友谊医院和中国医学科学院） ； Medical Intensive Care Unit, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Peking Union Medical College and Chinese Academy of Medical Sciences（医疗重症病房、复杂严重罕见疾病国家重点实验室、北京友谊医院、北京友谊医院和中国医学科学院） 纠错

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

AI总结 KRAL通过知识与推理增强学习提升LLM在临床抗菌治疗中的诊断能力，以低成本高效方式优化医疗决策支持。

CorrectHDL: Agentic HDL Design with LLMs Leveraging High-Level Synthesis as Reference

CorrectHDL: 基于LLM的代理HDL设计利用高层次综合作为参考

Kangwei Xu, Grace Li Zhang, Ulf Schlichtmann, Bing Li

机构 * Technical University of Munich (TUM)（慕尼黑技术大学） ； Technical University of Darmstadt（达姆施塔特技术大学） ； Technical University of Ilmenau（伊尔梅恩艾大学） 纠错

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

AI总结 CorrectHDL利用LLM和HLS结合，通过参考设计纠正生成错误，提升HDL设计的面积和功率效率，接近人工设计水平。

Comments 7 pages, 15 figures, 2 tables

Securing AI Agents Against Prompt Injection Attacks

保护AI代理免受提示注入攻击

Badrinath Ramakrishnan, Akshaya Balaji

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

AI总结 本文提出了一种多层防御框架，通过评估RAG系统中的提示注入风险，将攻击成功率降低至8.7%，同时保持高任务性能。

SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literature

Hang Ding, Yilun Zhao, Tiansheng Hu, Manasi Patwardhan, Arman Cohan

机构 * Shanghai Jiao Tong University（上海交通大学） ； Yale University（耶鲁大学） ； NYU Shanghai（纽约大学上海分校） ； TCS Research（TCS研究） 纠错

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

Artificial Intelligence Agents in Music Analysis: An Integrative Perspective Based on Two Use Cases

Antonio Manuel Martínez-Heredia, Dolores Godrid Rodríguez, Andrés Ortiz García

机构 * Dpto. Ingeniería de Comunicaciones, Universidad de Málaga, Campus de Teatinos（通信工程系，马拉加大学，泰蒂诺校区） ； Universidad Rey Juan Carlos（雷乌安卡洛斯大学） 纠错

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

Comments Extended version of the conference paper presented at SATMUS 2025

JobSphere: An AI-Powered Multilingual Career Copilot for Government Employment Platforms

Srihari R, Adarsha B, Mohammed Usman Hussain, Shweta Singh

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

Comments 7 pages, 4 figures, 4 tables

Journal ref Published in IEEE NQComp 2026

DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents

Qi Li, Jianjun Xu, Pingtao Wei, Jiu Li, Peiqiang Zhao, Jiwei Shi, Xuan Zhang, Yanhui Yang, Xiaodong Hui, Peng Xu, Wenqin Shao

机构 * Beijing Caizhi Tech（北京彩智科技） 纠错

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

Evaluating LLM-based Workflows for Switched-Mode Power Supply Design

Simon Nau, Jan Krummenauer, André Zimmermann

机构 * Robert Bosch GmbH, Cross-Domain Computing Solutions（罗伯特·博世有限公司，跨领域计算解决方案） ； University of Stuttgart, Institute for Micro Integration (IFM)（斯图加特大学，微系统集成研究所） ； Hahn-Schickard, Stuttgart, Germany（哈恩-施克尔德研究所，斯图加特，德国） 纠错

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

LLM-based Multi-class Attack Analysis and Mitigation Framework in IoT/IIoT Networks

Seif Ikbarieh, Maanak Gupta, Elmahedi Mahalal

机构 * Department of Computer Science Tennessee Tech University（计算机科学系田纳西科技大学） 纠错

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

A Comparison of Conversational Models and Humans in Answering Technical Questions: the Firefox Case

Joao Correia, Daniel Coutinho, Marco Castelluccio, Caio Barbosa, Rafael de Mello, Anita Sarma, Alessandro Garcia, Marco Gerosa, Igor Steinmacher

机构 * Pontifical Catholic University（天主教大学） ； Mozilla Corporation（Mozilla公司） ； Federal University of Rio de Janeiro（里约热内卢联邦大学） ； Oregon State University（俄勒冈州立大学） ； Northern Arizona University（北亚利桑那大学） 纠错

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

Comments 13 pages

IM-Chat: A Multi-agent LLM Framework Integrating Tool-Calling and Diffusion Modeling for Knowledge Transfer in Injection Molding Industry

Junhyeong Lee, Joon-Young Kim, Heekyu Kim, Inhyo Lee, Seunghwa Ryu

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

ECG-LLM -- training and evaluation of domain-specific large language models for electrocardiography

Lara Ahrens, Wilhelm Haverkamp, Nils Strodthoff

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

Comments 34 pages, 8 figures, code available at https://github.com/AI4HealthUOL/ecg-llm

SpareCodeSearch: Searching for Code Context When You Have No Spare GPU

Minh Nguyen

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

Comments 4 pages, 3 figures, 4 tables. Accepted to Context Collection Workshop co-located with ASE'25

LegalWiz: A Multi-Agent Generation Framework for Contradiction Detection in Legal Documents

Ananya Mantravadi, Shivali Dalmia, Olga Pospelova, Abhishek Mukherji, Nand Dave, Anudha Mittal

机构 * Centific ； Amazon（亚马逊） 纠错

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

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search

Nick Hagar, Nicholas Diakopoulos, Jeremy Gilbert

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

Comments Accepted to Computation + Journalism Symposium 2025

AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges

Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee

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

Journal ref Information Fusion, 2025

Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models

Sina J. Semnani, Jirayu Burapacheep, Arpandeep Khatua, Thanawan Atchariyachanvanit, Zheng Wang, Monica S. Lam

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

Comments EMNLP 2025 (Main Conference)

AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning

Amy Xin, Jinxin Liu, Zijun Yao, Zhicheng Lee, Shulin Cao, Lei Hou, Juanzi Li

机构 * Tsinghua University（清华大学） 纠错

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

AI-driven formative assessment and adaptive learning in data-science education: Evaluating an LLM-powered virtual teaching assistant

Fadjimata I Anaroua, Qing Li, Yan Tang, Hong P. Liu

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

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning

Yiting Wang, Wanghao Ye, Ping Guo, Yexiao He, Ziyao Wang, Bowei Tian, Shwai He, Guoheng Sun, Zheyu Shen, Sihan Chen, Ankur Srivastava, Qingfu Zhang, Gang Qu, Ang Li

机构 * University of Maryland, College Park（马里兰大学科帕克分校） ； City University of Hong Kong（香港城市大学） ； University of Southern California（南加州大学） 纠错

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

Comments NeurIPS 2025

A review of faithfulness metrics for hallucination assessment in Large Language Models

Ben Malin, Tatiana Kalganova, Nikoloas Boulgouris

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

Comments 13 pages, 6 tables

LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering

Boris Kovalerchuk, Brent D. Fegley

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

Comments 25 pages,4 figures, 2 tables

Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection

Jerry Li, Evangelos Papalexakis

机构 * University of California, Riverside（加州大学河滨分校） 纠错

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

SAMVAD: A Multi-Agent System for Simulating Judicial Deliberation Dynamics in India

Prathamesh Devadiga, Omkaar Jayadev Shetty, Pooja Agarwal

机构 * PES University（PES大学） 纠错

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

LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability Analysis

Reza Fayyazi, Michael Zuzak, Shanchieh Jay Yang

机构 * Rochester Institute of Technology（罗切斯特技术学院） ； Gonzaga University（戈兹加大学） 纠错

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