用安全约束的图演化生成更稳定可执行的智能体工作流
MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
- 将工作流建模为可验证的梅尔马德图，提升可读性与正确性
- 在基准测试中成功率显著提升，且更快收敛到可执行计划
- 适合需要高可靠性与可解释性的自主智能体系统开发者
尽管自主智能体推理前景广阔，现有工作流生成方法常因大模型驱动的无约束构建导致脆弱、不可执行的计划。我们提出 MermaidFlow，通过安全约束的图演化重新定义智能体搜索空间。核心是使用梅尔马德（Mermaid）这一结构化、人类可读的图语言，将工作流表示为可验证的中间表示。设计领域感知的演化算子，包括交叉、变异、插入和删除，在保持语义正确的同时促进结构多样性，从而高效探索高质量、静态可验证的工作流空间。无需修改任务设定或评估协议，MermaidFlow 在智能体推理基准上实现了成功率持续提升，并加速可执行计划的收敛。实验表明，安全约束的图演化为鲁棒、可解释的智能体推理系统提供了可扩展、模块化的基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。