Zheng, C., Pu, Y., Chen, J., Lyu, Y., Ng, W. Z. T., Zhang, H., Ong, Y., Tsang, I., & Yin, H. (n.d.). MermaidFlow: Redefining agentic workflow generation via Safety-Constrained Evolutionary Programming. International Conference on Machine Learning (ICML 2025)
Abstract:
Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the agentic search space through safety-constrained graph evolution. At its core, MermaidFlow represent workflows as a verifiable intermediate representation using Mermaid, a structured and human-interpretable graph language. We formulate domain-aware evolutionary operators, i.e., crossover, mutation, insertion, and deletion, to preserve semantic correctness while promoting structural diversity, enabling efficient exploration of a high-quality, statically verifiable workflow space. Without modifying task settings or evaluation protocols, MermaidFlow achieves consistent improvements in success rates and faster convergence to executable plans on the agent reasoning benchmark. The experimental results demonstrate that safety-constrained graph evolution offers a scalable, modular foundation for robust and interpretable agentic reasoning systems.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Career Development Fund (CDF)
Grant Reference no. : C233312007
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Career Development Fund (CDF)
Grant Reference no. : C243512014
This research / project is supported by the National Research Foundation, Singapore - AI Singapore Programme
Grant Reference no. : AISG-NMLP-2024-003