Flow: Modularized Agentic Workflow Automation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929725630316544 |
|---|---|
| author | Niu, Boye Song, Yiliao Lian, Kai Shen, Yifan Yao, Yu Zhang, Kun Liu, Tongliang |
| author_facet | Niu, Boye Song, Yiliao Lian, Kai Shen, Yifan Yao, Yu Zhang, Kun Liu, Tongliang |
| contents | Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An effective workflow adjustment is crucial in real-world scenarios, as the initial plan must adjust to unforeseen challenges and changing conditions in real time to ensure the efficient execution of complex tasks. In this paper, we define workflows as an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by LLM agents through dynamic subtask allocation adjustment based on historical performance and previous AOVs. To further enhance framework performance, we emphasize modularity in workflow design based on evaluating parallelism and dependency complexity. With this design, our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance. Empirical results across various practical tasks demonstrate significant improvements in the efficiency of multi-agent frameworks through dynamic workflow refinement and modularization. The code is available at: https://github.com/tmllab/2025_ICLR_FLOW. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Flow: Modularized Agentic Workflow Automation Niu, Boye Song, Yiliao Lian, Kai Shen, Yifan Yao, Yu Zhang, Kun Liu, Tongliang Artificial Intelligence Machine Learning Multiagent Systems Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An effective workflow adjustment is crucial in real-world scenarios, as the initial plan must adjust to unforeseen challenges and changing conditions in real time to ensure the efficient execution of complex tasks. In this paper, we define workflows as an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by LLM agents through dynamic subtask allocation adjustment based on historical performance and previous AOVs. To further enhance framework performance, we emphasize modularity in workflow design based on evaluating parallelism and dependency complexity. With this design, our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance. Empirical results across various practical tasks demonstrate significant improvements in the efficiency of multi-agent frameworks through dynamic workflow refinement and modularization. The code is available at: https://github.com/tmllab/2025_ICLR_FLOW. |
| title | Flow: Modularized Agentic Workflow Automation |
| topic | Artificial Intelligence Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2501.07834 |