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.

翻译：本文提出BPMN Assistant，这是一种利用大语言模型通过自然语言创建和编辑BPMN图的工具。虽然直接生成XML是常见做法，但其表述冗长、速度缓慢，且在复杂修改时容易产生语法错误。我们引入了一种专门设计的基于JSON的中间表示方法，旨在通过函数调用促进原子化编辑操作。我们使用一套包含GPT-5.1、Claude 4.5 Sonnet和DeepSeek V3在内的前沿模型，将我们的方法与直接XML操作进行了对比评估。结果表明，在编辑任务中，基于JSON的方法显著优于直接XML处理，在所有评估模型上取得了更高或相当的成功率。此外，尽管需要更多输入上下文，我们的方法将生成延迟降低了约43%，输出标记数量减少了75%以上，为交互式流程建模提供了更可靠、响应更快的解决方案。