Agent-Enhanced Large Language Models for Researching Political Institutions
It addresses the problem of high research costs for political science scholars by providing a domain-specific tool, though it is incremental as it builds on existing LLM and RAG methods.
This paper tackles the challenge of applying Large Language Models (LLMs) to political science research by augmenting them with predefined functions and tools, resulting in the development of CongressRA, an LLM agent that streamlines tasks like data collection and analysis for studying the U.S. Congress, reducing costs for replicating and extending empirical research.
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 for interaction with external knowledge bases. Beyond information retrieval, LLM agents may incorporate modular tools for tasks like document summarization, transcript coding, qualitative variable 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.