# A Skill-Based AI Agentic Pipeline for Library of Congress Subject Indexing

arXiv: https://arxiv.org/abs/2605.03537 · HTML: https://mlsanity.com/paper/2605.03537/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 6 of 6)

- [SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog](https://mlsanity.com/paper/2504.07199/) (2025)
- [Annif at SemEval-2025 Task 5: Traditional XMTC augmented by LLMs](https://mlsanity.com/paper/2504.19675/) (2025)
- [An Experiment with the Use of ChatGPT for LCSH Subject Assignment on Electronic Theses and Dissertations](https://mlsanity.com/paper/2403.16424/) (2024)
- [Kratt: Developing an Automatic Subject Indexing Tool for The National Library of Estonia](https://mlsanity.com/paper/2203.12998/) (2022)
- [An Extreme Multi-label Text Classification (XMTC) Library Dataset: What if we took "Use of Practical AI in Digital Libraries" seriously?](https://mlsanity.com/paper/2603.10876/) (2026)
- [Better Recommendations: Validating AI-generated Subject Terms Through LOC Linked Data Service](https://mlsanity.com/paper/2508.00867/) (2025)

## Built on by (most cited first, 1 of 1)

- [LCSHBench: A Multilingual, Consensus-Grounded Benchmark for Library of Congress Subject Heading Assignment](https://mlsanity.com/paper/2606.04382/) (2026)

## Abstract (arXiv)

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. Each skill encodes domain knowledge drawn directly from Library of Congress Subject Headings Manual (SHM) instruction sheets and subject analysis theory. The pipeline was evaluated against a corpus of ten titles whose existing subject headings were captured from the Harvard Library bibliographic dataset (a snapshot of their Alma ILS). Results demonstrate strong conceptual alignment with professional subject indexing practice, with notable differences in specificity, subdivision practice, and the agent's adherence to the 2026 LC policy discontinuing form subdivisions in favor of LCGFT 655 fields.