Towards Agentic Defect Reasoning: A Graph-Assisted Retrieval Framework for Laser Powder Bed Fusion

TL;DR

This paper introduces a graph-assisted retrieval framework that transforms literature into a knowledge graph to improve defect reasoning in Laser Powder Bed Fusion, enabling transparent and accurate identification of defect mechanisms.

Contribution

It presents a novel framework combining semantic and graph-based retrieval with agent-based reasoning to interpret defect pathways in LPBF from literature.

Findings

Achieved high retrieval accuracy and recall of 0.9667.

Enabled transparent reasoning chains linking parameters to defects.

Provided a scalable method for converting literature into an interpretable knowledge resource.

Abstract

Laser Powder Bed Fusion (LPBF) is highly sensitive to process parameters, which influence defect formation through complex thermal and fluid mechanisms. However, defect-related knowledge is dispersed across the literature, limiting systematic understanding. This study presents a graph-assisted retrieval framework for defect reasoning in LPBF, using Ti6Al4V as a case study. Scientific publications are transformed into a structured representation, and relationships between parameters, mechanisms, and defects are encoded into an evidence-linked knowledge graph. The framework integrates semantic and graph-based retrieval, supported by a lightweight agent-based reasoning layer to construct interpretable defect pathways. Evaluation shows high retrieval accuracy (0.9667) and recall (0.9667), demonstrating effective identification of relevant defect related evidence. The framework enables transparent reasoning chains linking process parameters to defects. This work provides a scalable approach for converting unstructured literature into a query able and interpretable knowledge resource for additive manufacturing.