Abstract
Large-scale scientific collaborations, such as the Compact Muon Solenoid (CMS) at CERN, produce a vast and ever-growing corpus of internal documentation. Navigating this complex information landscape presents a significant challenge for both new and experienced researchers, hindering knowledge sharing and slowing down the pace of scientific discovery. To address this, we present a prototype of MITRA, a Retrieval-Augmented Generation (RAG) based system, designed to answer specific, context-aware questions about physics analyses. MITRA employs a novel, automated pipeline using Selenium for document retrieval from internal databases and Optical Character Recognition (OCR) with layout parsing for high-fidelity text extraction. Crucially, MITRA's entire framework, from the embedding model to the Large Language Model (LLM), is hosted on-premise, ensuring that sensitive collaboration data remains private. We introduce a two-tiered vector database architecture that first identifies the relevant analysis from abstracts before focusing on the full documentation, resolving potential ambiguities between different analyses. We demonstrate the prototype's superior retrieval performance against a standard keyword-based baseline on realistic queries and discuss future work towards developing a comprehensive research agent for large experimental collaborations.
Abstract (translated)
大规模的科学合作项目，如欧洲核子研究组织（CERN）的紧凑型缪子线圈（CMS），产生了大量的内部文档，并且这些文档还在不断增长。对于新旧研究人员来说，在这个复杂的知识体系中导航是一项重大挑战，这阻碍了知识共享并减缓了科学研究的步伐。为了解决这个问题，我们介绍了一种名为MITRA的原型系统，这是一个基于检索增强生成（RAG）的设计，旨在回答关于物理分析的具体、上下文感知的问题。 MITRA采用了一条新颖且自动化的管道，使用Selenium从内部数据库中提取文档，并利用光学字符识别（OCR）和布局解析技术进行高质量文本抽取。至关重要的是，MITRA的整个框架，包括嵌入模型到大型语言模型（LLM），都部署在本地服务器上，确保敏感的合作数据保持私密。 我们介绍了一种两级向量数据库架构：首先通过摘要来识别相关分析，然后聚焦于完整文档，解决不同分析之间的潜在歧义问题。我们在实际查询中展示了原型系统的检索性能优于标准关键词基础线，并讨论了开发全面研究代理的未来工作的方向，以服务于大规模实验合作项目。
URL
https://arxiv.org/abs/2603.09800
