AI RESEARCH
A Skill-Based AI Agentic Pipeline for Library of Congress Subject Indexing
arXiv CS.AI
•
ArXi:2605.03537v1 Announce Type: cross This paper presents a modular AI agentic skill pipeline for automating subject indexing with Library of Congress Subject Headings (LCSH). Subject indexing - the process of analyzing a work's aboutness, selecting controlled vocabulary terms, and encoding them as MARC21 subject access fields - is one of the most time-consuming components of library cataloging. The system decomposes this process into four discrete, sequentially executed agent skills: conceptual analysis, quantitative filtering, authority validation, and MARC field synthesis.