# FlowMind: Automatic Workflow Generation with LLMs

arXiv: https://arxiv.org/abs/2404.13050 · HTML: https://mlsanity.com/paper/2404.13050/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 17 Mar 2024.

## Builds on (most cited first, 9 of 9)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023)
- [Modular Visual Question Answering via Code Generation](https://mlsanity.com/paper/2306.05392/) (2023)

## Built on by (most cited first, 30 of 30)

- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [Benchmarking Agentic Workflow Generation](https://mlsanity.com/paper/2410.07869/) (2024)
- [ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration](https://mlsanity.com/paper/2502.00675/) (2025)
- [LiteSearch: Efficacious Tree Search for LLM](https://mlsanity.com/paper/2407.00320/) (2024)
- [ChemGraph: An Agentic Framework for Computational Chemistry Workflows](https://mlsanity.com/paper/2506.06363/) (2025)
- [Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents](https://mlsanity.com/paper/2506.07388/) (2025)
- [Self-Organizing Agent Network for LLM-based Workflow Automation](https://mlsanity.com/paper/2508.13732/) (2025)
- [Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach](https://mlsanity.com/paper/2407.15788/) (2024)
- [MAO: A Framework for Process Model Generation with Multi-Agent Orchestration](https://mlsanity.com/paper/2408.01916/) (2024)
- [HiddenTables & PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies](https://mlsanity.com/paper/2406.10803/) (2024)
- [LAW: Legal Agentic Workflows for Custody and Fund Services Contracts](https://mlsanity.com/paper/2412.11063/) (2024)
- [Digital Player: Evaluating Large Language Models based Human-like Agent in Games](https://mlsanity.com/paper/2502.20807/) (2025)
- [Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows](https://mlsanity.com/paper/2505.24189/) (2025)
- [Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding](https://mlsanity.com/paper/2602.00854/) (2026)
- [FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning](https://mlsanity.com/paper/2410.19727/) (2024)
- [Bridging Language Models and Financial Analysis](https://mlsanity.com/paper/2503.22693/) (2025)
- [Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation](https://mlsanity.com/paper/2604.05150/) (2026)
- [No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Size](https://mlsanity.com/paper/2408.01444/) (2024)
- [StarFlow: Generating Structured Workflow Outputs From Sketch Images](https://mlsanity.com/paper/2503.21889/) (2025)
- [Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language](https://mlsanity.com/paper/2604.19667/) (2026)
- [WorkTeam: Constructing Workflows from Natural Language with Multi-Agents](https://mlsanity.com/paper/2503.22473/) (2025)
- [Action Engine: Automatic Workflow Generation in FaaS](https://mlsanity.com/paper/2411.19485/) (2024)
- [Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines](https://mlsanity.com/paper/2412.14684/) (2024)
- [Classifier-Augmented Generation for Structured Workflow Prediction](https://mlsanity.com/paper/2510.12825/) (2025)
- [From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents](https://mlsanity.com/paper/2603.07496/) (2026)
- [From Words to Workflows: Automating Business Processes](https://mlsanity.com/paper/2412.03446/) (2024)
- [What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance](https://mlsanity.com/paper/2602.20300/) (2026)
- [Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution](https://mlsanity.com/paper/2607.14456/) (2026)
- [Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs](https://mlsanity.com/paper/2608.30250/) (2026)
- [DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis](https://mlsanity.com/paper/2609.11504/) (2026)

## Abstract (arXiv)

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.