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

• URL: http://arxiv.org/abs/2604.04208v1
• Date: Sun, 05 Apr 2026 18:01:31 GMT
• Title: Towards Agentic Defect Reasoning: A Graph-Assisted Retrieval Framework for Laser Powder Bed Fusion
• Abstract summary: This study presents a graph-assisted retrieval framework for defect reasoning in Laser Powder Bed Fusion.<n>The framework integrates semantic and graph-based retrieval, supported by a lightweight agent-based reasoning layer.<n>The framework enables transparent reasoning chains linking process parameters to defects.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Generative artificial intelligence for reliable mechanistic reasoning for corrosion [0.0]
  This work presents a domain-adapted retrieval-augmented generation framework for corrosion knowledge synthesis.<n>Three open-weight language models are fine-tuned on 3,309 expert-verified question-answer pairs from 840 peer-reviewed papers.<n>Retrieval augmentation produces Token F1 gains of 143-194%, with system faithfulness of 0.964 and context recall of 0.988.
  arXiv  Detail & Related papers  (2026-08-31T15:15:17Z)
• A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion [0.0]
  This work presents a knowledge-driven system that integrates structured defect knowledge with LLM-based reasoning to provide explainable defect diagnosis and mitigation guidance.<n>The proposed system is built on a knowledge base containing 27 known LPBF defect types organized into hierarchical categories and causal relationships.
  arXiv  Detail & Related papers  (2026-05-01T21:12:51Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention [14.165510655766944]
  We develop a novel identifiability theorem, leveraging causal representation learning, to uncover disentangled representations of system parameters.<n>We instantiate system parameter identification as a variational inference problem, leveraging a sparsity-regularised transformer to uncover state-dependent causal structures.
  arXiv  Detail & Related papers  (2026-03-15T17:03:34Z)
• Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents [64.43980129731587]
  We propose a causal-inspired inference-time debiasing method called Causal Diagnosis and Correction (CDC)<n>CDC first diagnoses the bias effect of the perplexity and then separates the bias effect from the overall relevance score.<n> Experimental results across three domains demonstrate the superior debiasing effectiveness.
  arXiv  Detail & Related papers  (2025-03-11T17:59:00Z)
• CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference [2.147995542780459]
  This paper formulates super-resolution using structural causal models to reason about image degradation processes.<n>We propose a novel counterfactual learning strategy that leverages semantic guidance to reason about hypothetical degradation scenarios.<n>Our approach achieves significant improvements over state-of-the-art methods, particularly in challenging scenarios with compound degradations.
  arXiv  Detail & Related papers  (2025-01-27T08:19:17Z)
• A Multimodal Fusion Framework for Bridge Defect Detection with Cross-Verification [0.0]
  This paper introduces a multimodal fusion framework for the detection and analysis of bridge defects.<n>It integrates Non-Destructive Evaluation (NDE) techniques with advanced image processing to enable precise structural assessment.
  arXiv  Detail & Related papers  (2024-12-23T20:33:34Z)
• Mind the Gap: Analyzing Lacunae with Transformer-Based Transcription [2.486161976966064]
  We employ transformer-based optical character recognition (OCR) models trained on synthetic data containing lacunae. We demonstrate their effectiveness in detecting and restoring lacunae, achieving a success rate of 65%.
  arXiv  Detail & Related papers  (2024-06-28T22:52:39Z)
• Extending Complex Logical Queries on Uncertain Knowledge Graphs [50.360531130930646]
  The study of machine learning-based logical query answering enables reasoning with large-scale and incomplete knowledge graphs.<n>We propose a neural symbolic approach that incorporates both forward inference and backward calibration to answer soft queries on large-scale, incomplete, and uncertain knowledge graphs.
  arXiv  Detail & Related papers  (2024-03-03T13:13:53Z)
• Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic [51.967603572656266]
  We introduce a consistent and theoretically grounded approach to annotating decompositional entailment. We find that our new dataset, RDTE, has a substantially higher internal consistency (+9%) than prior decompositional entailment datasets. We also find that training an RDTE-oriented entailment classifier via knowledge distillation and employing it in an entailment tree reasoning engine significantly improves both accuracy and proof quality.
  arXiv  Detail & Related papers  (2024-02-22T18:55:17Z)
• Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies [58.179981892921056]
  This work introduces a novel principle for disentanglement we call mechanism sparsity regularization. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors. We show that the latent factors can be recovered by regularizing the learned causal graph to be sparse.
  arXiv  Detail & Related papers  (2024-01-10T02:38:21Z)
• A Discrepancy Aware Framework for Robust Anomaly Detection [51.710249807397695]
  We present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies. Our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance.
  arXiv  Detail & Related papers  (2023-10-11T15:21:40Z)
• Probabilistic Bearing Fault Diagnosis Using Gaussian Process with Tailored Feature Extraction [10.064000794573756]
  Rolling bearings are subject to various faults due to its long-time operation under harsh environment. Current deep learning methods perform the bearing fault diagnosis in the form of deterministic classification. We develop a probabilistic fault diagnosis framework that can account for the uncertainty effect in prediction.
  arXiv  Detail & Related papers  (2021-09-19T18:34:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.