Cascading automata to improve efficiency of large language models agents with GraphRAG for error analysis

Abstract

Robotic process automation (RPA) has been deployed in a plethora of industries, including the banking and insurance sectors. However, the key challenge of handling unexpected situations manifests either as an inadequacy of programming (since all situations cannot possibly be foreseen) or incongruous inputs. In parallel, deep learning models, including large language models (LLMs) and visual language models (VLMs), have shown human-like cognitive capabilities in real-world tasks, germinating the field of agentic LLMs. However, their computational expense, slow inference times, and massive energy consumption impede large-scale usage. We propose a framework that combines the two approaches to enable expedient invocation of LLMs for handling exceptions and supervising RPA bots. It aims to minimize the need for human supervision by “meta” automation, while also reducing energy usage and processing time. The automation workflow is presented as a graph, and our pipeline uses the GraphRAG framework to analyze and fix errors. We demonstrate the potential of our pipeline through two real-world examples in the banking and insurance sectors, provide our GitHub repository for reproducibility, and conclude with future research directions.