FlowMind: Automatic Workflow Generation with LLMs

TL;DR

FlowMind leverages Large Language Models to automatically generate workflows in Robotic Process Automation, addressing unpredictability and confidentiality issues, and incorporates user feedback for improved performance.

Contribution

This paper introduces FlowMind, a novel LLM-based system for automatic workflow generation that enhances RPA in unpredictable scenarios while ensuring data security.

Findings

FlowMind effectively generates workflows that handle spontaneous tasks.

User feedback improves workflow accuracy and relevance.

FlowMind outperforms baseline methods in benchmarks.

Abstract

The rapidly evolving field of Robotic Process Automation (RPA) has made significant strides in automating repetitive processes, yet its effectiveness diminishes in scenarios requiring spontaneous or unpredictable tasks demanded by users. This paper introduces a novel approach, FlowMind, leveraging the capabilities of Large Language Models (LLMs) such as Generative Pretrained Transformer (GPT), to address this limitation and create an automatic workflow generation system. In FlowMind, we propose a generic prompt recipe for a lecture that helps ground LLM reasoning with reliable Application Programming Interfaces (APIs). With this, FlowMind not only mitigates the common issue of hallucinations in LLMs, but also eliminates direct interaction between LLMs and proprietary data or code, thus ensuring the integrity and confidentiality of information - a cornerstone in financial services. FlowMind further simplifies user interaction by presenting high-level descriptions of auto-generated workflows, enabling users to inspect and provide feedback effectively. We also introduce NCEN-QA, a new dataset in finance for benchmarking question-answering tasks from N-CEN reports on funds. We used NCEN-QA to evaluate the performance of workflows generated by FlowMind against baseline and ablation variants of FlowMind. We demonstrate the success of FlowMind, the importance of each component in the proposed lecture recipe, and the effectiveness of user interaction and feedback in FlowMind.