Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution
For developers and organizations automating business processes, this work demonstrates that specialist agents can provide substantial gains in reliability, efficiency, and cost over generalist agents, though the problem is domain-specific.
The paper investigates whether specialist agents outperform generalist LLM-based agents for structured code workflow execution, specifically transforming BPMN diagrams into executable workflows. The specialist solution achieves 9-20 percentage points higher tool-use exactness, 2-4x better penalty-adjusted latency, 3x fewer tool-call errors, and over 95% reduction in generation token cost, eliminating repair iterations.
Large Language Models (LLMs) have accelerated the adoption of software development agents, now widely available as Integrated Development Environment (IDE) extensions and standalone applications. While these agents are typically general-purpose, it remains unclear whether specialist agents justify their additional development effort. We investigate this question in the context of business process automation, focusing on the transformation of Business Process Model and Notation (BPMN) diagrams into executable agentic workflows. Since BPMN specifies explicit control-flow semantics, we focus on deterministic workflows in which a fixed process model and inputs uniquely determine the executed path. We introduce a specialist workflow for this task and compare it against generalist agents such as Roo and Cline. Our results show that the specialist solution produces agents that outperform generalist baselines by approximately 9-20 percentage points in tool-use exactness, 2-4x in penalty-adjusted latency, and 3x fewer tool-call errors, while reducing generation token cost by over 95% and eliminating repair iterations. We also find that generalist agents generate code inconsistently in both functionality and quality, limiting their suitability for industrial settings where reliability and maintainability are essential.