FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910020152590336 |
|---|---|
| author | Liu, Yihao Zhang, Ziyun He, Zile Cai, Huaqian |
| author_facet | Liu, Yihao Zhang, Ziyun He, Zile Cai, Huaqian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11782 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning Liu, Yihao Zhang, Ziyun He, Zile Cai, Huaqian Artificial Intelligence Software Engineering 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. |
| title | FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2602.11782 |