RAG / 检索增强生成

DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning

DSL-R1：从SQL到DSL，通过强化学习在结构化和非结构化数据上训练检索代理

Yunhai Hu, Junwei Zhou, Yumo Cao, Yitao Long, Yiwei Xu, Qiyi Jiang, Weiyao Wang, Xiaoyu Cao, Zhen Sun, Yiran Zou, Nan Du

机构 * New York University（纽约大学） ； Matter Innovation Inc.（Matter创新公司） ； Thin Red Line（薄红线） 纠错

专题命中 图谱与结构化RAG ：hybrid retrieval(abstract)；分类 cs.IR、cs.AI、cs.DB

AI总结 本文提出DSL-R1框架，结合逻辑推理与语义匹配，通过强化学习优化DSL生成，提升检索性能，实现在结构化和非结构化数据上的改进。

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems

提示控制流完整性：一种优先级感知的运行时防御，用于对抗LLM系统中的提示注入

Md Takrim Ul Alam, Akif Islam, Mohd Ruhul Ameen, Abu Saleh Musa Miah, Jungpil Shin

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文提出Prompt Control-Flow Integrity，一种优先级感知的运行时防御机制，通过结构化组合系统、开发者、用户和检索文档片段来防范提示注入攻击，实现零误报率和低开销。

Comments 4 Figures, 3 Tables, Submitted to the International Conference on Power, Electronics, Communications, Computing, and Intelligent Infrastructure 2026

Large Language Model-driven Analysis of General Coordinates Network (GCN) Circulars

基于大语言模型的通用坐标网络（GCN）圆周分析

Vidushi Sharma, Ronit Agarwala, Judith L. Racusin, Leo P. Singer, Tyler Barna, Eric Burns, Michael W. Coughlin, Dakota Dutko, Courey Elliott, Rahul Gupta, Ashish Mahabal, Nikhil Mukund

专题命中 图谱与结构化RAG ：retrieval augmented generation(abstract)；RAG(abstract)

AI总结 本文利用大语言模型自动解析GCN圆周，实现暂现体观测信息的高效提取与分类，准确率达97.2%。

Comments 21 pages, 11 figures, 7 tables. Published in ApJS

Journal ref The Astrophysical Journal Supplement Series, 2026, Volume 283, Number 1, Pages 30

HAVEN: High-Bandwidth Flash Augmented Vector Engine for Large-Scale Approximate Nearest-Neighbor Search Acceleration

HAVEN：高带宽闪存增强向量引擎用于大规模近似最近邻搜索加速

Po-Kai Hsu, Weihong Xu, Qunyou Liu, Tajana Rosing, Shimeng Yu

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 HAVEN通过高带宽闪存增强GPU，实现大规模近似最近邻搜索加速，提升重新排序吞吐量和效率。

Comments *Po-Kai Hsu and Weihong Xu contributed equally to this work

Context-Augmented Code Generation Using Programming Knowledge Graphs

基于编程知识图谱的上下文增强代码生成

Shahd Seddik, Fahd Seddik, Iman Saberi, Fatemeh Fard, Minh Hieu Huynh, Patanamon Thongtanunam

机构 * University of British Columbia（不列颠哥伦比亚大学） ； University of Melbourne（墨尔本大学） 纠错

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文提出编程知识图谱（PKG）和重排序机制，通过细粒度检索和减少幻觉，提升代码生成在复杂问题上的表现。

Bridging Expert Reasoning and LLM Detection: A Knowledge-Driven Framework for Malicious Packages

弥合专家推理与大语言模型检测：一种基于知识的恶意包检测框架

Wenbo Guo, Shiwen Song, Jiaxun Guo, Zhengzi Xu, Chengwei Liu, Haoran Ou, Mengmeng Ge, Yang Liu

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 IntelGuard通过整合专家推理与大语言模型，实现高准确率的恶意包检测，发现54个未报告恶意包。

Lightweight LLMs for Network Attack Detection in IoT Networks

轻量级大语言模型用于物联网网络中的网络攻击检测

Piyumi Bhagya Sudasinghe, Kushan Sudheera Kalupahana Liyanage, Harsha S. Gardiyawasam Pussewalage

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文提出利用轻量级大语言模型结合QLoRA和RAG技术，实现高效的物联网网络攻击检测，展示在未知攻击类型上的零样本能力。

Comments 6 pages with 2 figures, This paper was accepted and presented at the 7th Computing, Communications and IoT Applications Conference (ComComAp 2025), held in Madrid, Spain, during 14th to 17th December 2025

Rethinking On-Device LLM Reasoning: Why Analogical Mapping Outperforms Abstract Thinking for IoT DDoS Detection

重新思考设备端LLM推理：为什么类比映射优于抽象思维用于IoT DDoS检测

William Pan, Guiran Liu, Binrong Zhu, Qun Wang, Yingzhou Lu, Beiyu Lin, Rose Qingyang Hu

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文提出一种结合Co_T和RAG的物联网边缘DDoS检测框架，通过示例驱动推理提升小型ODLLMs在资源受限下的检测性能。

CSQL: Mapping Documents into Causal Databases

CSQL：将文档映射到因果数据库

Sridhar Mahadevan

机构 * Adobe Research and University of Massachusetts（Adobe研究院和马萨诸塞大学） 纠错

专题命中 图谱与结构化RAG ：RAG(abstract)；分类 cs.IR、cs.AI、cs.DB

AI总结 CSQL通过将文档转换为因果数据库，支持对文档集合的因果分析，能够回答‘为什么’的问题，并实现大规模语料库级别的因果查询和纵向分析。

Comments 26 pages

RecipeMasterLLM: Revisiting RoboEarth in the Era of Large Language Models

RecipeMasterLLM: 重新审视大语言模型时代的RoboEarth

Asil Kaan Bozcuoglu, Ziyuan Liu

机构 * Huawei Heisenberg Research Center (Munich)（华为海森堡研究中心（慕尼黑）） 纠错

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 RecipeMasterLLM通过微调大语言模型实现自动化知识获取，提升机器人动作描述的准确性与一致性。

LA-RL: Language Action-guided Reinforcement Learning with Safety Guarantees for Autonomous Highway Driving

LA-RL: 基于语言动作引导的安全强化学习用于自动驾驶高速公路驾驶

Yiming Shu, Jiahui Xu, Jiwei Tang, Ruiyang Gao, Chen Sun

专题命中 图谱与结构化RAG ：retrieval augmented generation(abstract)；RAG(abstract)

AI总结 LA-RL通过整合大语言模型的语义推理和改进的安全层，提升自动驾驶高速公路驾驶的效率与安全性。

Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding

通过理解完成：利用多粒度理解引导代码生成

Xinkui Zhao, Rongkai Liu, Yifan Zhang, Chen Zhi, Lufei Zhang, Guanjie Cheng, Yueshen Xu, Shuiguang Deng, Jianwei Yin

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 CoCo通过多粒度理解引导代码生成，利用结构化上下文提升代码补全质量，实验表明其在多个基准测试中表现优异。

AutoPatch: Multi-Agent Framework for Patching Real-World CVE Vulnerabilities

AutoPatch：多智能体框架用于修补现实世界中的CVE漏洞

Minjae Seo, Wonwoo Choi, Myoungsung You, Seungwon Shin

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 AutoPatch通过多智能体框架高效修补LLM生成代码中的CVE漏洞，实现高准确率和低成本的漏洞修复

Comments 19 pages, double column, 9 figures. Under submission

From Reviewers' Lens: Understanding Bug Bounty Report Invalid Reasons with LLMs

从评审视角：利用大语言模型理解漏洞赏金报告无效原因

Jiangrui Zheng, Yingming Zhou, Ali Abdullah Ahmad, Hanqing Yao, Xueqing Liu

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 利用大语言模型和结构化评审知识，研究如何识别和解释漏洞赏金报告的无效原因，以提高报告质量和评审一致性。

Comments 10 pages, 4 figures

LLM-driven Provenance Forensics for Threat Investigation and Detection

Kunal Mukherjee, Murat Kantarcioglu

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Automated Vulnerability Validation and Verification: A Large Language Model Approach

Alireza Lotfi, Charalampos Katsis, Elisa Bertino

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective Distractors

Nicy Scaria, Silvester John Joseph Kennedy, Diksha Seth, Ananya Thakur, Deepak Subramani

机构 * Indian Institute of Science（印度科学研究院） 纠错

专题命中 图谱与结构化RAG ：RAG(abstract)；分类 cs.CL、cs.AI、cs.DB

Comments Accepted to ECAI 2025

Journal ref The European Conference on Artificial Intelligence. 413 (2025). pp 4089--4096. IOS Press

OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews

Mir Tafseer Nayeem, Davood Rafiei

专题命中 图谱与结构化RAG ：RAG(abstract)；分类 cs.IR、cs.CL、cs.AI

Comments COLM 2025

A Method for Quantifying Human Risk and a Blueprint for LLM Integration

Giuseppe Canale

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

LogSage: An LLM-Based Framework for CI/CD Failure Detection and Remediation with Industrial Validation

Weiyuan Xu, Juntao Luo, Tao Huang, Kaixin Sui, Jie Geng, Qijun Ma, Isami Akasaka, Xiaoxue Shi, Jing Tang, Peng Cai

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments 12 pages, 8 figures

Memory-Augmented Log Analysis with Phi-4-mini: Enhancing Threat Detection in Structured Security Logs

Anbi Guo, Mahfuza Farooque

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Poster: ChatIYP: Enabling Natural Language Access to the Internet Yellow Pages Database

Vasilis Andritsoudis, Pavlos Sermpezis, Ilias Dimitriadis, Athena Vakali

机构 * Aristotle University of Thessaloniki Thessaloniki Greece ； Measurement Lab\ for Science \& Society Portland OR United States ； Aristotle University of Thessaloniki ； Measurement Lab\ for Science \& Society 纠错

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments ACM Internet Measurement Conference (IMC) 2025

TraceRAG: A LLM-Based Framework for Explainable Android Malware Detection and Behavior Analysis

Guangyu Zhang, Xixuan Wang, Shiyu Sun, Peiyan Xiao, Kun Sun, Yanhai Xiong

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Socially Interactive Agents for Preserving and Transferring Tacit Knowledge in Organizations

Martin Benderoth, Patrick Gebhard, Christian Keller, C. Benjamin Nakhosteen, Stefan Schaffer, Tanja Schneeberger

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments 4 pages, 2 figures

Using LLMs and Essence to Support Software Practice Adoption

Sonia Nicoletti, Paolo Ciancarini

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Automated Label Placement on Maps via Large Language Models

Harry Shomer, Jiejun Xu

机构 * University of Texas at Arlington（德克萨斯理工大学） ； HRL Laboratories（HRL实验室） 纠错

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Workshop on AI for Data Editing (AI4DE) at KDD 2025

Snap, Segment, Deploy: A Visual Data and Detection Pipeline for Wearable Industrial Assistants

Di Wen, Junwei Zheng, Ruiping Liu, Yi Xu, Kunyu Peng, Rainer Stiefelhagen

机构 * Computer Vision for Human-Computer Interaction Lab (cv:hci)（人机交互视觉实验室） ； Institute for Anthropomatics and Robotics (IAR)（人机学与机器人研究所） ； Karlsruhe Institute of Technology（卡尔斯鲁厄技术大学） 纠错

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

TimelyHLS: LLM-Based Timing-Aware and Architecture-Specific FPGA HLS Optimization

Nowfel Mashnoor, Mohammad Akyash, Hadi Kamali, Kimia Azar

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Zara: An LLM-based Candidate Interview Feedback System

Nima Yazdani, Aruj Mahajan, Ali Ansari

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments 11 pages, 8 figures

Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction

Charlie Campbell, Hao Mark Chen, Wayne Luk, Hongxiang Fan

专题命中 图谱与结构化RAG ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Paper accepted by DAC'25