RAG / 检索增强生成

Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packages

众手成炬：基于LLM的多智能体系统用于检测恶意PyPI包

Muhammad Umar Zeshan, Motunrayo Ibiyo, Claudio Di Sipio, Phuong T. Nguyen, Davide Di Ruscio

专题命中 检索器与排序 ：RAG(abstract)

AI总结 本文提出LAMPS，一种基于LLM的多智能体系统，通过协作检测恶意PyPI包，实现高准确率和显著的性能提升。

Comments The paper has been peer-reviewed and accepted for publication to the Journal of Systems and Software (https://www.sciencedirect.com/journal/journal-of-systems-and-software)

Cognitive AI framework 2.0: advances in the simulation of human thought

认知AI框架2.0：人类思维模拟的进展

Rommel Salas-Guerra

专题命中 检索器与排序 ：retrieval augmented generation(abstract)

AI总结 认知AI框架2.0通过统一的记忆架构和受控的知识更新，提升人机交互的个性化与适应性，解决可扩展性、偏见缓解和伦理合规等挑战。

Federated Customization of Large Models: Approaches, Experiments, and Insights

联邦大模型定制化：方法、实验与洞察

Yuchuan Ye, Ming Ding, Youjia Chen, Peng Cheng, Dusit Niyato

机构 * College of Physics and Information Engineering, Fuzhou University（物理与信息工程学院，福州大学） ； Data61, CSIRO（Data61，CSIRO） ； Department of Computer Science and Information Technology, La Trobe University（计算机科学与信息科技系，拉筹夫大学） ； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

AI总结 本文提出联邦学习中的大模型定制化方法，通过实验验证了前缀微调的有效性，展示了其在性能、效率和鲁棒性方面的竞争力。

Comments 8 pages, 1 figure

Automating API Documentation from Crowdsourced Knowledge

从众包知识自动化生成API文档

Bonan Kou, Zijie Zhou, Muhao Chen, Tianyi Zhang

专题命中 检索器与排序 ：dense retrieval(abstract)

AI总结 AutoDoc通过从Stack Overflow提取API知识，生成更准确、简洁且全面的API文档，有效解决官方文档过时和不完整的问题。

Comments 13 pages, 2 figures, Accepted to ICSE 2026

SwarmFoam: An OpenFOAM Multi-Agent System Based on Multiple Types of Large Language Models

SwarmFoam: 基于多种大语言模型的开放FOAM多智能体系统

Chunwei Yang, Yankai Wang, Jianxiang Tang, Haojie Qu, Ziqiang Zou, YuLiu, Chunrui Deng, Zhifang Qiu, Ming Ding

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

AI总结 SwarmFoam通过整合多模态感知与智能校正技术，提升复杂CFD模拟的适应性与准确性。

Comments 26 pages, 15 figures

Impact of friction force and retrieval speed on in silico mechanical thrombectomies: a sensitivity analysis

摩擦力和取栓速度对计算机机械取栓的影响：灵敏度分析

Mahesh S. Nagargoje, Virginia Fregona, Giulia Luraghi, Francesco Migliavacca, Demitria A Poulos, Bryan C Good, Jose Felix Rodriguez Matas

专题命中 检索器与排序 ：retriever(abstract)

AI总结 研究探讨了摩擦力和取栓速度对机械取栓模拟的影响，发现摩擦系数和取栓速度变化会显著影响取栓效果，强调了准确计算摩擦因子在计算机模拟中的重要性。

Journal ref Computer Methods and Programs in Biomedicine 271 (2025) 109018

The role of friction forces in arterial mechanical thrombectomy: a review

摩擦力在动脉机械取栓中的作用：综述

Mahesh S. Nagargoje, Virginia Fregona, Giulia Luraghi, Francesco Migliavacca, Guglielmo Pero, Jose Felix Rodriguez Matas

专题命中 检索器与排序 ：retriever(abstract)

AI总结 本文综述了摩擦力在动脉机械取栓中的作用，指出富含纤维蛋白的血栓因摩擦系数高而更难取出，强调深入理解摩擦力对优化取栓技术的重要性。

Journal ref Journal of Biomechanics 192 (2025) 112966

ARBITER: AI-Driven Filtering for Role-Based Access Control

ARBITER: 基于人工智能的基于角色的访问控制过滤

Michele Lorenzo, Idilio Drago, Dario Salvadori, Fabio Romolo Vayr

专题命中 检索器与排序 ：RAG(abstract)

AI总结 ARBITER通过基于LLM的分层验证和角色感知检索，实现动态企业环境中高效的安全过滤。

LitFM: A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs

LitFM：一种基于检索增强的结构感知文献基础模型

Jiasheng Zhang, Jialin Chen, Ali Maatouk, Ngoc Bui, Qianqian Xie, Leandros Tassiulas, Jie Shao, Hua Xu, Rex Ying

专题命中 检索器与排序 ：retriever(abstract)

AI总结 LitFM是一种基于检索增强的结构感知文献基础模型，通过整合引用图结构和知识注入的LLM，提升文献检索和相关性评估的准确性。

Comments 12 pages, 8 figures

SoK: Can Fully Homomorphic Encryption Support General AI Computation? A Functional and Cost Analysis

SoK：完全同态加密能否支持通用人工智能计算？功能与成本分析

Jiaqi Xue, Xin Xin, Wei Zhang, Mengxin Zheng, Qianqian Song, Minxuan Zhou, Yushun Dong, Dongjie Wang, Xun Chen, Jiafeng Xie, Liqiang Wang, David Mohaisen, Hongyi Wu, Qian Lou

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

AI总结 本文探讨FHE能否支持通用AI计算，通过功能和成本分析评估了十种FHE方法，并针对混合线性和非线性操作的工作负载进行了基准测试。

Comments 26th Privacy Enhancing Technologies Symposium (PETS 2026)

Bita: A Conversational Assistant for Fairness Testing

Bita：一个用于公平性测试的对话助手

Keeryn Johnson, Cleyton Magalhaes, Ronnie de Souza Santos

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

AI总结 Bita是一个基于大型语言模型的对话助手，旨在通过公平性视角帮助软件测试人员检测偏见、评估测试计划并生成公平性导向的测试章程，提供可重复的公平性测试解决方案。

MG-Nav: Dual-Scale Visual Navigation via Sparse Spatial Memory

MG-Nav：基于稀疏空间记忆的双尺度视觉导航

Bo Wang, Jiehong Lin, Chenzhi Liu, Xinting Hu, Yifei Yu, Tianjia Liu, Zhongrui Wang, Xiaojuan Qi

机构 * The University of Hong Kong（香港大学） ； Southern University of Science and Technology（南方科技大学） 纠错

专题命中 检索器与排序 ：hybrid retrieval(abstract)

AI总结 MG-Nav通过稀疏空间记忆图和VGGT-adapter模块实现双尺度视觉导航，结合全局规划与局部控制，实现零样本导航的高鲁棒性与高性能。

Comments 10pages, 5 figures

Multi-Agent Debate Strategies to Enhance Requirements Engineering with Large Language Models

Marc Oriol, Quim Motger, Jordi Marco, Xavier Franch

专题命中 检索器与排序 ：retrieval augmented generation(abstract)

Aethorix v1.0: An Integrated Scientific AI Agent for Scalable Inorganic Materials Innovation and Industrial Implementation

Yingjie Shi, Yiru Gong, Yiqun Su, Suya Xiong, Jiale Han, Runtian Miao

专题命中 检索器与排序 ：knowledge retrieval(abstract)

Scalable Unit Harmonization in Medical Informatics via Bayesian-Optimized Retrieval and Transformer-Based Re-ranking

Jordi de la Torre

机构 * Data Science & Artificial Intelligence, Biopharma R&D（数据科学与人工智能、生物制药研发） ； AstraZeneca（阿斯利康） 纠错

专题命中 检索器与排序 ：hybrid retrieval(abstract)

Journal ref International Journal of Medical Informatics 206 (2026) 106180

Phase-Coded Memory and Morphological Resonance: A Next-Generation Retrieval-Augmented Generator Architecture

Denis V. Saklakov

专题命中 检索器与排序 ：RAG(abstract)

Comments 24 pages, 2 diagrams, conceptual white paper for cognitive AI and memory architecture research. Primary category cs.AI; secondary cs.NE and q-bio.NC

SCRUTINEER: Detecting Logic-Level Usage Violations of Reusable Components in Smart Contracts

Xingshuang Lin, Binbin Zhao, Jinwen Wang, Qinge Xie, Xibin Zhao, Shouling Ji

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

GraphMASAL: A Graph-based Multi-Agent System for Adaptive Learning

Biqing Zeng, Mengquan Liu, Zongwei Zhen

专题命中 检索器与排序 ：dense retrieval(abstract)

Comments 9 pages, 3 figures,submitted to AAMAS 2026

Oh That Looks Familiar: A Novel Similarity Measure for Spreadsheet Template Discovery

Anand Krishnakumar, Vengadesh Ravikumaran

机构 * Ekimetrics 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

Comments 5 pages, 2 figures, Accepted to EurIPS'25: AI for Tabular Data Workshop

Towards LLM-Powered Task-Aware Retrieval of Scientific Workflows for Galaxy

Shamse Tasnim Cynthia, Banani Roy

专题命中 检索器与排序 ：vector search(abstract)

R2ComSync: Improving Code-Comment Synchronization with In-Context Learning and Reranking

Zhen Yang, Hongyi Lin, Xiao Yu, Jacky Wai Keung, Shuo Liu, Pak Yuen Patrick Chan, Yicheng Sun, Fengji Zhang

专题命中 检索器与排序 ：hybrid retrieval(abstract)

gem5 Co-Pilot: AI Assistant Agent for Architectural Design Space Exploration

Zuoming Fu, Alex Manley, Mohammad Alian

专题命中 检索器与排序 ：retrieval augmented generation(abstract)

Comments Accepted by CAMS25, October, 2025, Seoul, Republic of Korea

A Design Science Blueprint for an Orchestrated AI Assistant in Doctoral Supervision

Teo Susnjak, Timothy R. McIntosh, Tong Liu, Paul Watters

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation

Philipp Bauerfeind, Amir Salarpour, David Fernandez, Pedram MohajerAnsari, Johannes Reschke, Mert D. Pesé

机构 * Clemson University（克莱姆森大学） 纠错

专题命中 检索器与排序 ：retriever(abstract)

Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification

Kumar Manas, Christian Schlauch, Adrian Paschke, Christian Wirth, Nadja Klein

机构 * Department of Mathematics and Computer Science, Freie Universität Berlin（自由大学柏林数学与计算机科学系） ； Continental Automotive Technologies GmbH, AI Lab Berlin（大陆汽车技术有限公司柏林AI实验室） ； Karlsruhe Institute of Technology, Scientific Computing Center, Methods for Big Data（卡尔斯鲁厄理工学院科学计算中心、大数据方法） ； Fraunhofer Institute for Open Communication Systems, Berlin, Germany（弗劳恩霍夫开放通信系统研究所，柏林德国） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

Comments 17 Pages, 9 figures. Accepted to Robotics: Science and Systems(RSS), 2025

Journal ref Robotics: Science and Systems (RSS), 2025

Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledge

Mohammad Saqib Hasan, Sayontan Ghosh, Dhruv Verma, Geoff Kuenning, Erez Zadok, Scott A. Smolka, Niranjan Balasubramanian

专题命中 检索器与排序 ：retriever(abstract)

Comments Accepted to COLM 2024

Complementarity, Augmentation, or Substitutivity? The Impact of Generative Artificial Intelligence on the U.S. Federal Workforce

William G. Resh, Yi Ming, Xinyao Xia, Michael Overton, Gul Nisa Gürbüz, Brandon De Bruhl

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

Comments 53 pages, 9 figures, 3 tables

InReAcTable: LLM-Powered Interactive Visual Data Story Construction from Tabular Data

Gerile Aodeng, Guozheng Li, Yunshan Feng, Qiyang Chen, Yu Zhang, Chi Harold Liu

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

Comments 16 pages, 10 figures, accepted at ACM UIST 2025 (to appear)

Bridging Solidity Evolution Gaps: An LLM-Enhanced Approach for Smart Contract Compilation Error Resolution

Likai Ye, Mengliang Li, Dehai Zhao, Jiamou Sun, Xiaoxue Ren

专题命中 检索器与排序 ：knowledge retrieval(abstract)

Comments International Conference on Software Maintenance and Evolution (ICSME) 2025

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

Naizhu Jin, Zhong Li, Tian Zhang, Qingkai Zeng

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)

Comments Accepted by SEKE 2025