LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911646872502272 |
|---|---|
| author | Eslaminia, Ahmadreza Cai, Chuhan Smith, Cameron Mei, Ruo-Syuan Li, Shichen Malhotra, Rajiv Nahrstedt, Klara Shao, Chenhui |
| author_facet | Eslaminia, Ahmadreza Cai, Chuhan Smith, Cameron Mei, Ruo-Syuan Li, Shichen Malhotra, Rajiv Nahrstedt, Klara Shao, Chenhui |
| contents | Additive manufacturing (AM) continues to transform modern manufacturing by enabling flexible, on-demand production of complex geometries across diverse industries. Fused filament fabrication (FFF) has extended AM to laboratories, classrooms, and small production environments, but this accessibility shifts process-planning responsibility to users who may lack manufacturing expertise. A syntactically valid slicer profile can still encode thermally or geometrically harmful settings, and subtle G-code edits can alter extrusion, cooling, or adhesion before a print begins. Pre-print G-code screening catches accidental or adversarial machine-program errors before material or machine time is wasted. This paper proposes LLM-ADAM as a generalizable LLM framework for pre-print anomaly detection in AM. The framework decomposes the task into three roles: Extractor-LLM maps a G-code file to a structured process-parameter schema; Reference-LLM converts printer and material documentation into aligned operating ranges; and Judge-LLM interprets a deterministic deviation table and G-code evidence to decide whether a part is non-defective or belongs to an anomaly class. Printers, materials, and LLM backbones are interchangeable test conditions, not fixed assumptions. We evaluate the framework on an N=200 FFF G-code corpus spanning two desktop printer families, two materials, and five classes including non-defective, under-extrusion, over-extrusion, warping, and stringing. The best framework configuration reaches 87.5% accuracy, compared with 59.5% for the strongest engineered single-LLM baseline. The results show that structured decomposition, rather than backbone strength alone, is the dominant source of improvement, with defect classes identified at or near ceiling for leading configurations while residual errors concentrate on conservative false alarms for non-defective samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03328 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing Eslaminia, Ahmadreza Cai, Chuhan Smith, Cameron Mei, Ruo-Syuan Li, Shichen Malhotra, Rajiv Nahrstedt, Klara Shao, Chenhui Machine Learning Artificial Intelligence Additive manufacturing (AM) continues to transform modern manufacturing by enabling flexible, on-demand production of complex geometries across diverse industries. Fused filament fabrication (FFF) has extended AM to laboratories, classrooms, and small production environments, but this accessibility shifts process-planning responsibility to users who may lack manufacturing expertise. A syntactically valid slicer profile can still encode thermally or geometrically harmful settings, and subtle G-code edits can alter extrusion, cooling, or adhesion before a print begins. Pre-print G-code screening catches accidental or adversarial machine-program errors before material or machine time is wasted. This paper proposes LLM-ADAM as a generalizable LLM framework for pre-print anomaly detection in AM. The framework decomposes the task into three roles: Extractor-LLM maps a G-code file to a structured process-parameter schema; Reference-LLM converts printer and material documentation into aligned operating ranges; and Judge-LLM interprets a deterministic deviation table and G-code evidence to decide whether a part is non-defective or belongs to an anomaly class. Printers, materials, and LLM backbones are interchangeable test conditions, not fixed assumptions. We evaluate the framework on an N=200 FFF G-code corpus spanning two desktop printer families, two materials, and five classes including non-defective, under-extrusion, over-extrusion, warping, and stringing. The best framework configuration reaches 87.5% accuracy, compared with 59.5% for the strongest engineered single-LLM baseline. The results show that structured decomposition, rather than backbone strength alone, is the dominant source of improvement, with defect classes identified at or near ceiling for leading configurations while residual errors concentrate on conservative false alarms for non-defective samples. |
| title | LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.03328 |