用大模型生成流程图，比直接改代码快75%还更准
BPMN Assistant: An LLM-Based Approach to Business Process Modeling
- 用自定义JSON中间格式替代原始XML，支持精准修改
- 所有模型测试中成功率更高，生成延迟降43%，输出量少75%
- 适合需要快速迭代流程图的开发与业务人员
本文提出BPMN Assistant，一种基于大语言模型的自然语言驱动的BPMN流程图创建与编辑工具。直接生成XML虽常见，但冗长、缓慢且易出语法错误。为此，我们设计了一种专用的JSON中间表示，通过函数调用实现原子化编辑操作。在GPT-5.1、Claude 4.5 Sonnet和DeepSeek V3等先进模型上评估发现，相较于直接操作XML，JSON方法在所有模型上均显著提升编辑成功率，达到更高或相当的成功率。此外，尽管输入上下文增加约20%，该方法仍使生成延迟降低约43%，输出令牌数减少超过75%，为交互式流程建模提供了更可靠、更高效的解决方案。
原文摘要 · Abstract (English)
This paper presents BPMN Assistant, a tool that leverages Large Language Models for natural language-based creation and editing of BPMN diagrams. While direct XML generation is common, it is verbose, slow, and prone to syntax errors during complex modifications. We introduce a specialized JSON-based intermediate representation designed to facilitate atomic editing operations through function calling. We evaluate our approach against direct XML manipulation using a suite of state-of-the-art models, including GPT-5.1, Claude 4.5 Sonnet, and DeepSeek V3. Results demonstrate that the JSON-based approach significantly outperforms direct XML in editing tasks, achieving higher or equivalent success rates across all evaluated models. Furthermore, despite requiring more input context, our approach reduces generation latency by approximately 43% and output token count by over 75%, offering a more reliable and responsive solution for interactive process modeling.
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。