RobustFlow: Towards Robust Agentic Workflow Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916989929259008 |
|---|---|
| author | Xu, Shengxiang Zhang, Jiayi Di, Shimin Luo, Yuyu Yao, Liang Liu, Hanmo Zhu, Jia Liu, Fan Zhang, Min-Ling |
| author_facet | Xu, Shengxiang Zhang, Jiayi Di, Shimin Luo, Yuyu Yao, Liang Liu, Hanmo Zhu, Jia Liu, Fan Zhang, Min-Ling |
| contents | The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical, unaddressed challenge. Current methods often generate wildly inconsistent workflows when provided with instructions that are semantically identical but differently phrased. This brittleness severely undermines their reliability and trustworthiness for real-world applications. To quantitatively diagnose this instability, we propose metrics based on nodal and topological similarity to evaluate workflow consistency against common semantic variations such as paraphrasing and noise injection. Subsequently, we further propose a novel training framework, RobustFlow, that leverages preference optimization to teach models invariance to instruction variations. By training on sets of synonymous task descriptions, RobustFlow boosts workflow robustness scores to 70\% - 90\%, which is a substantial improvement over existing approaches. The code is publicly available at https://github.com/DEFENSE-SEU/RobustFlow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RobustFlow: Towards Robust Agentic Workflow Generation Xu, Shengxiang Zhang, Jiayi Di, Shimin Luo, Yuyu Yao, Liang Liu, Hanmo Zhu, Jia Liu, Fan Zhang, Min-Ling Multiagent Systems The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical, unaddressed challenge. Current methods often generate wildly inconsistent workflows when provided with instructions that are semantically identical but differently phrased. This brittleness severely undermines their reliability and trustworthiness for real-world applications. To quantitatively diagnose this instability, we propose metrics based on nodal and topological similarity to evaluate workflow consistency against common semantic variations such as paraphrasing and noise injection. Subsequently, we further propose a novel training framework, RobustFlow, that leverages preference optimization to teach models invariance to instruction variations. By training on sets of synonymous task descriptions, RobustFlow boosts workflow robustness scores to 70\% - 90\%, which is a substantial improvement over existing approaches. The code is publicly available at https://github.com/DEFENSE-SEU/RobustFlow. |
| title | RobustFlow: Towards Robust Agentic Workflow Generation |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2509.21834 |