专用智能体比通用模型更高效准确，专攻代码流程自动化
Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution
- 针对业务流程图生成可执行工作流，设计专用智能体系统
- 工具调用准确率高9-20%，延迟降低2-4倍，错误减少3倍
- 适合工业级应用，显著提升代码可靠性与维护性
大型语言模型（LLMs）加速了软件开发智能体的普及，现广泛作为集成开发环境（IDE）插件和独立应用存在。尽管这些智能体通常为通用型，但专用智能体是否值得额外开发仍不明确。本文聚焦于业务流程自动化，研究将业务流程模型与符号（BPMN）图转换为可执行的智能体工作流。由于BPMN具有明确的控制流语义，研究重点为确定性工作流——固定流程模型与输入唯一决定执行路径。本文提出一种专用工作流解决方案，并与Roo、Cline等通用智能体进行对比。结果表明，专用方案在工具调用精确度上比基线高出9-20个百分点，惩罚调整后延迟降低2-4倍，工具调用错误减少3倍，生成令牌成本降低超95%，且无需修复迭代。同时发现，通用智能体在功能和质量上生成代码不一致，限制其在对可靠性与可维护性要求高的工业场景中的适用性。
原文摘要 · Abstract (English)
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.
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。