cs.AINov 3, 2026

AgentAM: An AI Agent for Spatter- and Defect-Aware Process Optimization in Laser Powder Bed Fusion

Authors: Olabode T. Ajenifujah, Amir Barati Farimani

Organizations: Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USA · Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, 15213, PA, USA · Machine Learning Department, Carnegie Mellon University, Pittsburgh, 15213, PA, USA

Abstract

Predictive models for laser powder bed fusion (LPBF) are rarely used on the shop floor because querying them requires programming and model-specific knowledge. We present AgentAM, a large language model (LLM) agent that gives process engineers natural-language access to CFD-trained surrogates of spatter and melt pool geometry for SS316L through the Model Context Protocol (MCP). Polynomial surrogates trained on 279 single-track simulations predict melt pool dimensions (R2≥0.95R^2 \geq 0.95) and spatter volume (R2=0.83R^2 = 0.83 on test data) at any power-velocity point in the trained range, and geometric criteria assign each point a geometry-derived defect regime (keyhole, lack of fusion, balling or stable) that matches the regime obtained from the simulated geometry in 93.4% of tracks under cross-validation. The agent selects and parameterizes tools for prediction, process-window scans and constrained optimization. Minimum-spatter optima often sat within 10 μμm of the lack-of-fusion boundary; a margin-aware optimizer moved them away from all thresholds and raised the estimated probability of remaining classified Good from 0.94 to 1.00 under an assumed 2% process drift, and from 0.72 to 0.91 when jointly sampled cross-validated geometry residuals were added. About 40-50 well-spread simulations sufficed to reproduce the defect map. To evaluate the agent layer, we introduce a 145-prompt benchmark scored against direct tool calls, plus eight prompts (40 runs) on margin-aware requests. Over the 725 runs of the main benchmark the agent passed the intended inputs in 98.5% of parsing prompts, reported the scored spatter values and defect classes faithfully and met every stated constraint in the 65 feasible optimization runs, within a median 1.0% of the brute-force optimum.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

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

    Apr 5, 2026Muhammad Rizwan Awan, Volker Pickert, Muhammad Waqar Ashraf +3Additive ManufacturingGraph Retrieval-Augmented Generation

  2. A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion

    May 1, 2026Basit Mahmud Shahriar, Md Habibor RahmanIndustrial InspectionLLM Decision-Making

  3. Predicting Surface Displacement Fields of Laser Powder Bed Fusion Parts Using STL-Derived Graphs and Part-Level Descriptors

    Nov 19, 2026Saima Ahmed Suhi, Lang Yuan, Md Habibor RahmanAdditive Manufacturing