高技术通讯2026,Vol.36Issue(1):41-52,12.DOI:10.3772/j.issn.1002-0470.2026.01.004
基于应用程序接口依赖关系图路径搜索的工作流生成方法
Workflow generation method with path search on application programming interface dependency graph
摘要
Abstract
Workflow programming is increasingly becoming an important software development paradigm,and intelligent workflow generation services can offer users a more efficient development process.However,existing workflow de-velopment platforms only provide basic assistance,such as candidate node recommendations or edge connection constraints.Although large language model-driven intelligent programming services have made significant progress in code generation,there are still many challenges in the field of workflow generation.This paper analyzes the com-mon hallucination problems of large language models during workflow generation and proposes a workflow generation method based on application programming interface(API)dependency graph-guided path search.By using API dependency graph to guide the path search,the model's output decoding space is constrained,effectively mitiga-ting hallucinations.Furthermore,we introduce various path search strategies,including outbound and inbound path searches,providing a novel chain-of-thought approach for workflow generation.Experimental results show that the proposed method achieves better performance compared to previous chain-of-thought techniques,and significantly reduces model hallucinations.关键词
工作流生成/思维链/路径搜索/大语言模型幻觉/应用程序接口依赖关系图Key words
workflow generation/chain-of-thought/path search/large language model hallucinations/appli-cation programming interface dependency graph引用本文复制引用
梁冬,史骁,吕存驰,赵晓芳..基于应用程序接口依赖关系图路径搜索的工作流生成方法[J].高技术通讯,2026,36(1):41-52,12.基金项目
江苏省重大科研专项(BM2021800)和中国科学院计算技术研究所创新基金(E361060)资助项目. (BM2021800)