MermaidFlow-CF: How Agentic Workflow Representation Governs Constraint-Faithful Control

AAAI 2026 Workshop TrustAgent Submission57 Authors

Keywords: agentic workflow representation, constrained workflow optimization

TL;DR: We introduced Mermaid-CF, a framework defining constrained workflow optimization task and revealing the constraint-faithful control intrinsics of workflow representations.

Abstract: Agentic workflows coordinate LLM agents to autonomously generate, refine, and execute multi-step task pipelines, yet maintaining reliable control over instruction-following behavior remains challenging, often resulting in cascading workflow failures. These failures frequently stem from unconstrained workflow synthesis, where structural drift and broken control flow accumulate over time. In this paper, we show that a key driver of this brittleness is workflow representation, which determines whether planning structure and control flow can be preserved during generation, evaluation, and execution. We introduce MermaidFlow-CF, a constraint-faithful workflow optimization framework that represents workflows in a symbolic graph DSL Mermaid, enabling symbolic control-flow syntax that renders planning structure explicit and supports interpretable and checkable workflow generation. Building on this formulation, we formalize the constrained workflow optimization problem and introduce a structured taxonomy of workflow constraints spanning resource feasibility, executability, structural validity, and causal coherence. We further develop an evaluation protocol to measure constraint violation and correction dynamics for the constraints. Across multi-step reasoning benchmarks, MermaidFlow-CF achieves significantly higher constraint fidelity and markedly fewer cascading failures than AFlow, a Python-based workflow optimization baseline. These results show that symbolic workflow representations in Mermaid provide a more reliable foundation for agentic pipelines than Python, and that constraints function not as barriers but as structural priors that shape optimization dynamics and enable more stable, higher-performance optimization in agentic workflow planning.

Submission Number: 57