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

Key points

The authors integrated OData metadata and BPMN business processes into one typed property graph, giving service retrieval both sequential and schema constraints.
The hybrid retriever finds candidate endpoints with dense embeddings and then follows process edges to retrieve subsequent endpoints.
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.
On 81 multi-step queries, the agent completes 38.7% of tasks, compared with 10.3% for a chunk-based baseline.
Providing valid code lists as plain text eliminates invented codes but leaves invalid keys in 46% of write runs, while full typed context reduces invalid calls to 3% (3 of 101 runs), with no invented codes.
As a limitation, the authors state the evaluation is partly circular because the mock validator and the graph share the same metadata, so results must be reproduced against an independent backend.

External research summaries. These are not HDATF publications or measured product results.