超越通用语言模型：用于结构化代码工作流执行的专业代理系统
Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution
浏览论文内容
中文总结 AI 辅助
研究在业务流程自动化中，将BPMN图转换为可执行代理工作流时，专业代理是否值得额外开发。引入专业工作流并与通用代理比较，结果显示专业代理在多方面表现更优，通用代理代码生成不一致，不适用于工业环境。
中文摘要 AI 辅助
大语言模型加速了软件开发代理的应用，如今它们常作为集成开发环境扩展和独立应用程序广泛可用。虽然这些代理通常是通用的，但尚不清楚专业代理是否值得额外的开发努力。我们在业务流程自动化背景下研究这个问题，重点是将业务流程模型和符号图转换为可执行的代理工作流。由于BPMN指定了明确的控制流语义，我们专注于确定性工作流。我们为此任务引入了一个专业工作流，并将其与Roo和Cline等通用代理进行比较。结果表明，专业解决方案生成的代理在工具使用准确性上比通用基线高出约9 - 20个百分点，惩罚调整延迟快2 - 4倍，工具调用错误少3倍，同时生成令牌成本降低超过95%并消除修复迭代。我们还发现通用代理在功能和质量上生成代码不一致，限制了它们在可靠性和可维护性至关重要的工业环境中的适用性。
英文摘要
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.
