用意图层提升大模型生成复杂工作流的逻辑性与可靠性
Opus: A Prompt Intention Framework for Complex Workflow Generation
- 在用户查询与工作流生成间加入意图捕捉层，结构化理解多意图需求
- 在1000组合成数据上，工作流语义相似度显著提升，复杂查询下表现更稳定
- 适合需要精准执行复杂任务的开发者、自动化系统设计者使用
本文提出Opus提示意图框架，旨在提升基于指令微调的大语言模型在复杂工作流生成中的表现。该框架在用户查询与工作流生成之间引入中间的意图捕捉层，包含从查询中提取工作流信号、将其转化为结构化的意图对象，并基于此生成工作流。实验表明，该层使LLM能生成逻辑清晰、意义明确的工作流，且在查询复杂度上升时仍保持稳定性能。在包含1000组多意图查询-工作流对的合成基准测试中，采用该框架的工作流生成在语义相似度指标上持续取得改进。本文通过引入工作流信号与工作流意图概念，构建了可复现、可定制的基于LLM的意图捕捉系统，并提供了实证证据：相比直接从查询生成，该系统显著提升了工作流生成质量，尤其在混合意图提取场景下优势明显。
原文摘要 · Abstract (English)
This paper introduces the Opus Prompt Intention Framework, designed to improve complex Workflow Generation with instruction-tuned Large Language Models (LLMs). We propose an intermediate Intention Capture layer between user queries and Workflow Generation, implementing the Opus Workflow Intention Framework, which consists of extracting Workflow Signals from user queries, interpreting them into structured Workflow Intention objects, and generating Workflows based on these Intentions. Our results show that this layer enables LLMs to produce logical and meaningful outputs that scale reliably as query complexity increases. On a synthetic benchmark of 1,000 multi-intent query-Workflow(s) pairs, applying the Opus Prompt Intention Framework to Workflow Generation yields consistent improvements in semantic Workflow similarity metrics. In this paper, we introduce the Opus Prompt Intention Framework by applying the concepts of Workflow Signal and Workflow Intention to LLM-driven Workflow Generation. We present a reproducible, customizable LLM-based Intention Capture system to extract Workflow Signals and Workflow Intentions from user queries. Finally, we provide empirical evidence that the proposed system significantly improves Workflow Generation quality compared to direct generation from user queries, particularly in cases of Mixed Intention Elicitation.
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。