Journal of Political Institutions and Political Economy > Vol 6 > Issue 3–4

Agent-Enhanced Large Language Models for Researching Political Institutions

Joseph R. Loffredo, Department of Political Science, Massachusetts Institute of Technology, USA, loffredo@mit.edu , Suyeol Yun, Independent Researcher, USA, syyun@alum.mit.edu
 
Suggested Citation
Joseph R. Loffredo and Suyeol Yun (2025), "Agent-Enhanced Large Language Models for Researching Political Institutions", Journal of Political Institutions and Political Economy: Vol. 6: No. 3–4, pp 277-300. http://dx.doi.org/10.1561/113.00000125

Publication Date: 01 Oct 2025
© 2025 J. R. Loffredo and S. Yun
 
Subjects
Information extraction,  Natural language processing for IR,  Question answering,  Summarization,  Text mining,  Deep learning
 
Keywords
Large language modelsretrieval-augmented generationAI agentAgentic RAGpolitical institutions
 

Share

Download article
In this article:
Introduction 
The Potential of LLM Agents 
The Case for LLM Agents and the Study of Political Institutions 
Designing LLM Agents 
Example LLM Agent: CongressRA 
Further Potential Applications 
Discussion 
References 

Abstract

The applications of large language models (LLMs) in political science are rapidly expanding. This paper demonstrates how LLMs, when augmented with predefined functions and specialized tools, can serve as dynamic agents capable of streamlining tasks such as data collection, preprocessing, and analysis. Central to this approach is agentic retrieval-augmented generation (Agentic RAG), which equips LLMs with action-calling capabilities to interact with external knowledge bases. Beyond information retrieval, LLM agents may incorporate modular tools for tasks like document summarization, classification, and statistical modeling. To demonstrate the potential of this approach, we introduce CongressRA, an LLM agent designed to support scholars studying the U.S. Congress. Through this example, we highlight how LLM agents can reduce the costs of replicating, testing, and extending empirical research using the domain-specific data that drives the study of political institutions.

DOI:10.1561/113.00000125

Online Appendix | 113.00000125_app.pdf

This is the article's accompanying appendix.

DOI: 10.1561/113.00000125_app

Companion

Journal of Political Institutions and Political Economy, Volume 6, Issue 3-4 Special Issue: Artificial Intelligence and the Study of Political Institutions
See the other articles that are part of this special issue.