RAG / 检索增强生成

Japanese AI Agent System on Human Papillomavirus Vaccination: System Design

日本的人乳头瘤病毒疫苗人工智能代理系统：系统设计

Junyu Liu, Siwen Yang, Dexiu Ma, Qian Niu, Zequn Zhang, Momoko Nagai-Tanima, Tomoki Aoyama

机构 * Kyoto University（京都大学） ； University of Waterloo（滑铁卢大学） ； Texas Tech University（德克萨斯技术大学） ； The University of Tokyo（东京大学） ； USTC（中国科学技术大学） 纠错

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

AI总结 本研究设计了一种双用途的人工智能代理系统，通过对话界面提供HPV疫苗信息并生成分析报告，有效应对疫苗犹豫问题。

A Generalizable Framework for Building Executable Domain-Specific LLMs under Data Scarcity: Demonstration on Semiconductor TCAD Simulation

在数据稀缺条件下构建可执行领域特定大语言模型的通用框架：以半导体TCAD仿真为例

Di Wang, Zhenhua Wu, Yu Liu, Kai Chang, Shaohua Wu

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文提出一种通用框架，在数据稀缺条件下构建可执行的领域特定大语言模型，通过生成合成数据和代码优化流程，实现领域知识灌输和脚本可执行性提升。

Comments Submitted to Nature Computational Science

When Small Models Are Right for Wrong Reasons: Process Verification for Trustworthy Agents

当小模型适用于错误的原因：信任代理的过程验证

Laksh Advani

机构 * Laksh Advani 纠错

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文揭示小型语言模型在推理过程中的可靠性问题，提出推理完整性评分，并展示RAG提升推理质量而元认知可能损害性能，强调过程验证对可信代理的重要性。

Comments Accepted to Trustagent workshop AAAI 2026

StutterFuse: Mitigating Modality Collapse in Stuttering Detection with Jaccard-Weighted Metric Learning and Gated Fusion

StutterFuse: 通过Jaccard加权度量学习和门控融合缓解语塞崩溃

Guransh Singh, Md Shah Fahad

机构 * Department of Computer Science, Birla Institute of Technology, Mesra（计算机科学系，比拉理工学院，梅斯拉） 纠错

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 StutterFuse通过Jaccard加权度量学习和门控融合策略，有效缓解语塞检测中的模态崩溃问题，实现高精度多标签分类。

Comments 13 pages, 10 figures

Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus

Citegeist: 在arXiv语料库上自动生成相关工作分析的应用程序

Claas Beger, Carl-Leander Henneking

机构 * Cornell University（康奈尔大学） 纠错

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)

AI总结 Citegeist通过动态RAG技术在arXiv语料库上自动生成相关工作分析，结合嵌入相似性匹配、总结和多阶段过滤，提供引用支持的输出。

When Code Crosses Borders: A Security-Centric Study of LLM-based Code Translation

当代码跨越国界：一种以安全为中心的LLM代码翻译研究

Hailong Chang, Guozhu Meng, Shuhui Xiao, Kai Chen, Kun Sun, Yilin Li

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文研究了LLM在代码翻译中的安全风险，发现28.6%-45%的翻译引入新漏洞，并提出RAG策略降低漏洞率32.8%。

Beyond Code Similarity: Benchmarking the Plausibility, Efficiency, and Complexity of LLM-Generated Smart Contracts

超越代码相似性：评估LLM生成智能合约的可信度、效率和复杂性

Francesco Salzano, Simone Scalabrino, Rocco Oliveto, Remo Pareschi

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

AI总结 本文评估了LLM生成智能合约的可信度、效率和复杂性，发现检索增强生成显著提升了功能正确性，但生成代码仍需专家验证。

Comments 20 pages

Graph Neural Networks Based Analog Circuit Link Prediction

Guanyuan Pan, Tiansheng Zhou, Jianxiang Zhao, Zhi Li, Yugui Lin, Bingtao Ma, Yaqi Wang, Pietro Liò, Shuai Wang

机构 * HDU-ITMO Joint Institute, Hangzhou Dianzi University（杭州电子科技大学信息处理联合研究所） ； Intelligent Information Processing Laboratory, Hangzhou Dianzi University（杭州电子科技大学智能信息处理实验室） ； Innovation Center for Electronic Design Automation Technology, Hangzhou Dianzi University（杭州电子科技大学电子设计自动化技术创新中心） ； School of Computer Science and Technology, South China Business College, Guangdong University of Foreign Studies（广东外语外贸大学南方商学院计算机科学与技术学院） ； Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系） 纠错

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Code and data will be made available on request to the corresponding author

Journal ref Pan, G., Zhou, T., Zhao, J., Li, Z., Lin, Y., Ma, B., ... & Wang, S. (2026). Graph Neural Networks Based Analog Circuit Link Prediction. Engineering Applications of Artificial Intelligence, 163, 113035

RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation

Yang Liu, Li Zhang, Fang Liu, Zhuohang Wang, Donglin Wei, Zhishuo Yang, Kechi Zhang, Jia Li, Lin Shi

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Accepted by ICSE 2026

PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates

Yuan-An Xiao, Weixuan Wang, Dong Liu, Junwei Zhou, Shengyu Cheng, Yingfei Xiong

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments 13 pages, 5 figures; accepted for ICSE 2026

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows

Penghao Wang, Yuhao Zhou, Mengxuan Wu, Ziheng Qin, Bangyuan Zhu, Shengbin Huang, Xuanlei Zhao, Panpan Zhang, Xiaojiang Peng, Yuzhang Shang, Jianfei Yang, Zheng Zhu, Tianlong Chen, Zhangyang Wang, Kai Wang

机构 * NUS（国立新加坡大学） ； NTU（国立科技大学） ； SZTU（深圳技术大学） ； UCF（佛罗里达大学） ； GigaAI（GigaAI研究所） ； UNC（北卡罗来纳大学教堂山分校） ； UT Austin（得克萨斯大学奥斯汀分校） 纠错

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Towards an Efficient, Customizable, and Accessible AI Tutor

Juan Segundo Hevia, Facundo Arredondo, Vishesh Kumar

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments AAAI - iRAISE 2025

Generating High-Level Test Cases from Requirements using LLM: An Industry Study

Satoshi Masuda, Satoshi Kouzawa, Kyousuke Sezai, Hidetoshi Suhara, Yasuaki Hiruta, Kunihiro Kudou

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments 11pages

ADAM: A Diverse Archive of Mankind for Evaluating and Enhancing LLMs in Biographical Reasoning

Jasin Cekinmez, Omid Ghahroodi, Saad Fowad Chandle, Dhiman Gupta, Ehsaneddin Asgari

机构 * Qatar Computing Research Institute（卡塔尔计算研究所） ； Princeton University（普林斯顿大学） ； Virginia Tech（弗吉尼亚理工大学） ； Amity University（阿米蒂大学） 纠错

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

RuCCoD: Towards Automated ICD Coding in Russian

Aleksandr Nesterov, Andrey Sakhovskiy, Ivan Sviridov, Airat Valiev, Vladimir Makharev, Petr Anokhin, Galina Zubkova, Elena Tutubalina

机构 * AIRI ； Sber AI ； Skoltech ； Sber AI Lab ； HSE University（HSE大学） ； Innopolis University（Innopolis大学） ； ISP RAS Research Center for Trusted AI（ISP RAS可信AI研究中心） 纠错

专题命中 RAG评测 ：RAG(abstract)；分类 cs.CL、cs.AI、cs.DB

Comments Accepted to EMNLP 2025 (Main Conference)

BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text

Ibrahim Al Azher, Miftahul Jannat Mokarrama, Zhishuai Guo, Sagnik Ray Choudhury, Hamed Alhoori

机构 * Northern Illinois University（北伊利诺伊大学） ； University of North Texas（北德克萨斯大学） 纠错

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)

Comments 16 pages, 8 figures, Accepted to the 2025 Conference on Empirical Methods in Natural Language Processing (Findings)

SouLLMate: An Adaptive LLM-Driven System for Advanced Mental Health Support and Assessment, Based on a Systematic Application Survey

Qiming Guo, Jinwen Tang, Wenbo Sun, Haoteng Tang, Yi Shang, Wenlu Wang

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Accelerating Discovery: Rapid Literature Screening with LLMs

Santiago Matalonga, Domenico Amalfitano, Jean Carlo Rossa Hauck, Martín Solari, Guilherme H. Travassos

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)

Comments This version of the manuscript has been submitted to Empirical Software Engieering Journal for consideration

From Misunderstandings to Learning Opportunities: Leveraging Generative AI in Discussion Forums to Support Student Learning

Stanislav Pozdniakov, Jonathan Brazil, Oleksandra Poquet, Stephan Krusche, Santiago Berrezueta-Guzman, Shazia Sadiq, Hassan Khosravi

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Artificial Intelligence in Education (AIED 2025)

Journal ref Artificial Intelligence in Education. AIED 2025. Lecture Notes in Computer Science, vol 15882. Springer, Cham

SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation

M Zafir Sadik Khan, Nowfel Mashnoor, Mohammad Akyash, Kimia Azar, Hadi Kamali

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Accepted to the IEEE International Conference on Computer Design (ICCD 2025)

Humans are more gullible than LLMs in believing common psychological myths

Bevan Koopman, Guido Zuccon

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Can Large Language Models Be Trusted Paper Reviewers? A Feasibility Study

Chuanlei Li, Xu Hu, Minghui Xu, Kun Li, Yue Zhang, Xiuzhen Cheng

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)

AURA: A Multi-Agent Intelligence Framework for Knowledge-Enhanced Cyber Threat Attribution

Nanda Rani, Sandeep Kumar Shukla

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

PentestAgent: Incorporating LLM Agents to Automated Penetration Testing

Xiangmin Shen, Lingzhi Wang, Zhenyuan Li, Yan Chen, Wencheng Zhao, Dawei Sun, Jiashui Wang, Wei Ruan

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)

Comments 14 pages, 13 figures, AsiaCCS 2025

NextG-GPT: Leveraging GenAI for Advancing Wireless Networks and Communication Research

Ahmad M. Nazar, Mohamed Y. Selim, Daji Qiao, Hongwei Zhang

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Accepted in International Conference on Computer Communications and Networks (ICCCN 2025)

From Course to Skill: Evaluating LLM Performance in Curricular Analytics

Zhen Xu, Xinjin Li, Yingqi Huan, Veronica Minaya, Renzhe Yu

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware

Yujia Chen, Mingyu Chen, Cuiyun Gao, Zhihan Jiang, Zhongqi Li, Yuchi Ma

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments Accepted by FSE 2025 Industry Track

CXMArena: Unified Dataset to benchmark performance in realistic CXM Scenarios

Raghav Garg, Kapil Sharma, Karan Gupta

机构 * Sprinklr 纠错

专题命中 RAG评测 ：RAG(abstract)；分类 cs.IR、cs.CL、cs.AI

The Impact of Large Language Models on Task Automation in Manufacturing Services

Jochen Wulf, Juerg Meierhofer

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)

Comments arXiv admin note: text overlap with arXiv:2406.01407

From First Draft to Final Insight: A Multi-Agent Approach for Feedback Generation

Jie Cao, Chloe Qianhui Zhao, Xian Chen, Shuman Wang, Christian Schunn, Kenneth R. Koedinger, Jionghao Lin

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)

Comments 14 pages, to be published at the 26th International Conference on Artificial Intelligence in Education (AIED '25)