# FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning

arXiv: https://arxiv.org/abs/2602.11782 · HTML: https://mlsanity.com/paper/2602.11782/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 26 of 26)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://mlsanity.com/paper/2504.07086/) (2025)
- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [SciAgent: Tool-augmented Language Models for Scientific Reasoning](https://mlsanity.com/paper/2402.11451/) (2024)
- [StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows](https://mlsanity.com/paper/2403.11322/) (2024)
- [WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models](https://mlsanity.com/paper/2411.05451/) (2024)
- [DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI](https://mlsanity.com/paper/2512.16676/) (2025)
- [Blueprint First, Model Second: A Framework for Deterministic LLM Workflow](https://mlsanity.com/paper/2508.02721/) (2025)
- [United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory](https://mlsanity.com/paper/2506.06843/) (2025)
- [Benchmarking Failures in Tool-Augmented Language Models](https://mlsanity.com/paper/2503.14227/) (2025)
- [Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows](https://mlsanity.com/paper/2505.24189/) (2025)
- [STEPS: A Benchmark for Order Reasoning in Sequential Tasks](https://mlsanity.com/paper/2306.04441/) (2023)
- [AdaptFlow: Adaptive Workflow Optimization via Meta-Learning](https://mlsanity.com/paper/2508.08053/) (2025)
- [Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning](https://mlsanity.com/paper/2509.19517/) (2025)
- [AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science](https://mlsanity.com/paper/2502.16395/) (2025)
- [Scaling LLM Planning: NL2FLOW for Parametric Problem Generation and Rigorous Evaluation](https://mlsanity.com/paper/2507.02253/) (2025)
- [Opus: A Prompt Intention Framework for Complex Workflow Generation](https://mlsanity.com/paper/2507.11288/) (2025)
- [CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density](https://mlsanity.com/paper/2509.18458/) (2025)
- [Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data](https://mlsanity.com/paper/2508.18244/) (2025)
- [Classifier-Augmented Generation for Structured Workflow Prediction](https://mlsanity.com/paper/2510.12825/) (2025)

## Abstract (arXiv)

LLMs can solve complex tasks through reasoning and tool use, but accurately translating these solutions into structured workflows remains challenging. We model workflows as sequences of tool use and reformulate the problem as designing a mechanism that can both solve tasks and reliably construct workflows. Prior approaches that build workflows during execution often suffer from inaccuracies due to interference between the two processes. We propose an Execute-Summarize(ES) framework that decouples task execution from workflow construction: the model first completes the task using available tools, then independently reconstructs a structured workflow from execution traces. This separation improves workflow accuracy and robustness. We introduce FlowBench and show through extensive experiments that our approach outperforms existing methods, providing a reliable paradigm for grounding free-form LLM reasoning into structured workflows.