arXiv cs.AI· Garima Agrawal, Prasun Das, Akshay Sarvade, Priyanka L, Minisha N, Sravani Joshna, Hemath Manivannan, Lavanya Korada, Sambhrit Pattanayak, Srashti Gupta, Siddu R, Prasad Kalyanasundaram·· 2 小时前AI 评分43
面向多智能体系统的企业 RAG 重构：先组织再检索的知识层
Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves
AI 导读
arXiv 论文提出一个面向多智能体系统的企业级知识层，在检索前先对工件进行组织：通过自描述目录、稀疏元数据注册表和基于工件的导航超图，让查询解析为约束向量搜索的工件标识符，从而在结构上而非统计上完成消歧。该系统由七智能体逆向工程流水线支撑，处理 18 个服务的 241 个代码仓库，一周内建成，支持根因分析并在开发者验证下解决了 100+ 生产缺陷，还将 35 次发布回归失败归因到具体规则和服务。
正文 · 原文
Authors:Garima Agrawal, Prasun Das, Akshay Sarvade, Priyanka L, Minisha N, Sravani Joshna, Hemath Manivannan, Lavanya Korada, Sambhrit Pattanayak, Srashti Gupta, Siddu R, Prasad Kalyanasundaram
Abstract:Enterprises are deploying agentic AI across the software development lifecycle, and they need the behavioral logic of the systems they act on, not stakeholder documentation. A seven-agent reverse-engineering pipeline recovered this logic, processing 241 repositories across 18 services into thousands of artifacts describing scope, journeys, rules and acceptance criteria. Recovery does not confer usability. Entities like offer, eligibility, and activation recur across services under a shared vocabulary, related in name but operationally distinct, so one end-to-end journey implicates over a thousand near-identical rules that must not be conflated. Flat vector retrieval fails, returning an identical rule from the wrong service at high similarity with no signal of error. Content-level ontology, the traditional remedy, did not exist, and relating every occurrence of recurring entities would have cost more than the engagement and not survived a release cycle. We place the ontology at the artifact level. In this machine-generated corpus, each artifact retains its producer, component, service, domain and type, provenance that disambiguates before content is read. We present a knowledge layer that organizes before retrieving: a self-describing catalog, a sparse metadata registry, and a navigation hypergraph defined over artifacts rather than extracted entities. Queries resolve to artifact identifiers that constrain vector search, so the competing rule from another service is absent rather than outranked, making disambiguation structural, not statistical. Built in under a week and admitting new services by convention, the layer serves SDLC agents, developers, quality engineers and analysts. It supported root-cause analysis and resolution of 100+ production defects with developer verification and attributed 35 release regression failures to specific rules and services.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32851 [cs.AI] |
| (or arXiv:2610.32851v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32851 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Garima Agrawal [view email]
[v1]
Fri, 23 Oct 2026 16:21:56 UTC (546 KB)
来源：arXiv cs.AI · arxiv.org