FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning
This addresses the problem of reliable workflow generation from LLM reasoning for AI and automation applications, representing an incremental improvement over prior methods.
The paper tackles the challenge of accurately translating LLM reasoning into structured workflows by proposing an Execute-Summarize framework that decouples task execution from workflow construction, resulting in improved workflow accuracy and robustness as demonstrated on FlowBench.
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.