AgentAM: LLM Agent for Spatter- and Defect-Aware Process Optimization in Laser Powder Bed Fusion
AgentAM is an LLM agent that provides natural-language access to CFD-trained surrogate models for laser powder bed fusion (LPBF), enabling process engineers to query spatter and melt pool predictions without programming. The surrogates achieve high accuracy (R² ≥ 0.95 for melt pool, 0.83 for spatter) and defect classification matches simulated geometry in 93.4% of tracks. The agent successfully handles prediction, process-window scans, and constrained optimization, with margin-aware optimization improving robustness to process drift. A 145-prompt benchmark shows 98.5% parsing accuracy and faithful reporting.
Why it matters: This paper presents a concrete AI agent that bridges advanced predictive models with practical shop-floor use, demonstrating measurable performance improvements and a novel benchmark.