arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2603.09800cs.IRcs.AIcs.CLcs.LGhep-ex
收藏

MITRA：一种用于物理学协作中知识检索的AI助手

MITRA: An AI Assistant for Knowledge Retrieval in Physics Collaborations

Abhishikth Mallampalli, Sridhara Dasu

备注：
Accepted at NeurIPS 2025 Machine Learning for the Physical Sciences workshop and Lepton Photon conference 2025 (Computing AI/ML track)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

MITRA是一种基于RAG的AI助手，通过本地化框架实现物理学协作中的高效知识检索与生成。

摘要：

大规模的科学协作，例如位于欧洲核子研究中心的紧凑缪子对撞机（CMS），会产生大量且持续增长的内部文档库。在这一复杂的信患景观中，新旧研究人员都面临重大挑战，这阻碍了知识共享并减缓了科学发现的速度。为此，我们提出了MITRA的原型，这是一种基于检索增强生成（RAG）的系统，旨在回答关于物理分析的具体、上下文感知问题。MITRA采用了一种新颖的自动化流水线，使用Selenium从内部数据库中检索文档，并使用OCR与布局解析进行高保真的文本提取。关键的是，MITRA的整个框架，从嵌入模型到大型语言模型（LLM），均在本地托管，确保敏感的协作数据保持私密。我们引入了一种两级向量数据库架构，首先从摘要中识别相关的分析，然后再聚焦于完整的文档，解决不同分析之间可能的歧义。我们展示了原型在现实查询上的优越检索性能，与标准关键词基线相比，并讨论了未来工作，以开发一个全面的大型实验协作研究代理。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑