Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation

原文：Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation

作者：Saiful Khan, Afrah Farea

来源：arXiv cs.AI（人工智能）

正文

Computer Science > Artificial Intelligence

arXiv:2610.37242v1 (cs)

[Submitted on 27 Oct 2026]

Title:Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation

Authors:Saiful Khan, Afrah Farea

View a PDF of the paper titled Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation, by Saiful Khan and Afrah Farea

View PDF

HTML (experimental)

Abstract:Large language model (LLM) agents that call enterprise APIs must select the correct endpoints, follow process order, use valid payload keys, and choose coded values from predefined lists. However, current retrieval-augmented service discovery treats endpoints independently and therefore misses process and schema constraints. We address this limitation by integrating Open Data Protocol (OData) metadata and Business Process Model and Notation (BPMN) reference processes in a typed property graph. A hybrid retriever identifies candidate endpoints using dense embeddings and follows process edges to retrieve subsequent endpoints. We evaluate the method on 42 enterprise services with process-chain ground truth. For queries with low lexical overlap between the query and downstream entities, it improves Recall@3 by 5.7 points (n=74), with consistent gains across embedding models and cut-offs. It matches dense retrieval on other queries and provides no improvement on OpenAPI services without a process layer, indicating that the gains arise from process structure. We also evaluate an LLM agent on 81 multi-step queries. It completes 38.7% of tasks, compared with 10.3% for a chunk-based baseline. In an elicitation probe, providing valid code lists eliminates invented codes but leaves invalid keys in 46% of write runs. Full typed context reduces invalid calls to 3% (3 of 101 runs), with no invented codes. These results show that exposing process and schema constraints during retrieval improves the reliability of agent-driven API calls.

Subjects:

Artificial Intelligence (cs.AI); Software Engineering (cs.SE)

Cite as:

arXiv:2610.37242 [cs.AI]

(or

arXiv:2610.37242v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.37242

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

人工智能 · 软件工程

由「前沿雷达」于 2026-10-27 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。