Language models to assess printability in additive manufacturing: a future perspective

Abstract

Large language models and vision-language models have the potential to change how printability is assessed in additive manufacturing. By learning from the rapidly expanding body of literature, process logs, simulation outputs, and image-based defect data, these models can move printability evaluation from trial-and-error experimentation to scalable, knowledge-rich reasoning across materials and processes. They can classify and explain defects, link them to process-parameter choices, and act as intelligent supervisors that suggest targeted process-variable adjustments while integrating physics-based simulations and specialized machine-learning models. At the same time, realizing this potential requires new multimodal printability datasets, physics-preserving algorithms, rigorous uncertainty quantification, and benchmarking frameworks, as well as exploration of advanced computational infrastructures, including quantum-inspired approaches for high-dimensional optimization. This perspective outlines how language models can capture human expertise, unify heterogeneous data, and enable more reliable, data-driven printability decisions for next-generation metal additive manufacturing.

Keywords

Large language model / Vision-language model / Machine learning / Defects / 3D printing / Quantum computing / Uncertainty quantification

References

[1] DebRoy T, Mukherjee T. Digital Twins of Advanced Materials Processing. Amsterdam, The Netherlands: Elsevier; 2026. doi: 10.1016/C2023-0-51329-1

[2] Mukherjee T, DebRoy T. Theory and Practice of Additive Manufacturing. Hoboken, NJ, USA: John Wiley & Sons; 2023. doi: 10.1002/9781394442942

[3] Mukherjee T ed. The Science and Technology of 3D Printing. Basel, Switzerland: MDPI; 2021. doi: 10.3390/books978-3-0365-2584-6

[4] Mukherjee T. Recent progress in process, structure, properties, and performance in additive manufacturing. Sci Technol Weld Join. 2023; 28(9):941-945. doi: 10.1080/13621718.2023.2253588

[5] Mukherjee T, Elmer JW, Wei HL, et al. Control of grain structure, phases, and defects in additive manufacturing of high-performance metallic components. Prog Mater Sci. 2023; 138:101153. doi: 10.1016/j.pmatsci.2023.101153

[6] Sheikh S, Vela B, Honarmandi P, et al. High-throughput alloy and process design for metal additive manufacturing. npj Comput Mater. 2025; 11(1):179. doi: 10.1038/s41524-025-01670-x

[7] Erinle TJ, Uguru-Okorie DC, Adebimpe AM, Adediran AA, Eze HU. A comprehensive review of in-situ monitoring and post-process defect detection in additive manufacturing. FUDMA J Eng Technol. 2026; 2(1):744-767.

[8] Gao Z, Yu W, Liu K. A Review on Solidification Cracking of Welding Aluminum Alloys: Mechanism, Influencing Factors and Crack Resistance of Filler Metal. Coatings. 2026; 16(4):464. doi: 10.3390/coatings16040464

[9] Zhang Y, Wu S, Guo Z, Peng G, Wang L, Yan W. Defects caused by powder spattering and entrainment in laser powder bed fusion process: High-fidelity modeling of gas, melt pool and powder dynamics. Acta Mater. 2025; 288:120816. doi: 10.1016/j.actamat.2025.120816

[10] Khan NA, Chakraborty D, Srivatsan TS, Kumar A. Recent Progress in the Friction Stir Additive Manufacturing: Process Parameters, Microstructural Evolution, and Mechanical Performance. Trans Indian Inst Met. 2025; 78(9):219. doi: 10.1007/s12666-025-03702-y

[11] Agapovichev AV, Khaimovich AI, Smelov VG, et al. Optimization of L-PBF Process Parameters for Defect Reduction and Mechanical Strength of Ni-Cr-Mo-Nb Superalloy Using Multi-Objective Methods. Materials. 2025; 18(8):1743. doi: 10.3390/ma18081743

[12] Altun F, Bayar A, Hamzat AK, Asmatulu R, Ali Z, Asmatulu E. AI-Driven Innovations in 3D Printing: Optimization, Automation, and Intelligent Control. J Manuf Mater Process. 2025; 9(10):329. doi: 10.3390/jmmp9100329

[13] Rojek I, Mikołajewski D, Kempiński M, Galas K, Piszcz A. Emerging Applications of Machine Learning in 3D Printing. Appl Sci. 2025; 15(4):1781. doi: 10.3390/app15041781

[14] Sinha S, Mukherjee T. Mitigation of Gas Porosity in Additive Manufacturing Using Experimental Data Analysis and Mechanistic Modeling. Materials. 2024; 17(7):1569. doi: 10.3390/ma17071569

[15] Wang W, Ning J, Liang SY. Analytical Prediction of Balling, Lack-of-Fusion and Keyholing Thresholds in Powder Bed Fusion. Appl Sci. 2021; 11(24):12053. doi: 10.3390/app112412053

[16] Wu SH, Tariq U, Joy R, Sparks T, Flood A, Liou F. Experimental, Computational, and Machine Learning Methods for Prediction of Residual Stresses in Laser Additive Manufacturing: A Critical Review. Materials. 2024; 17(7):1498. doi: 10.3390/ma17071498

[17] Yeganeh M, Shahryari Z, Talib Khanjar A, Hajizadeh Z, Shabani F. Inclusions and Segregations in the Selective Laser-Melted Alloys: A Review. Coatings. 2023; 13(7):1295. doi: 10.3390/coatings13071295

[18] Ashrafizadeh SM, Habibnejad-Korayem M, Yue S. Influence of particle size distribution on the rheological properties and spreadability of plasma-atomized powders. Mater Today Commun. 2025; 49:114426. doi: 10.1016/j.mtcomm.2025.114426

[19] Iams AD, Weaver JS, Lane BM, et al. Microstructural features and metastable phase formation in a high-strength aluminum alloy fabricated using additive manufacturing. J Alloys Compd. 2025; 1025:180281. doi: 10.1016/j.jallcom.2025.180281

[20] Zhan J, Li K, Ma R, et al. Achieving fine tailoring of elastocaloric properties of laser powder bed-fused NiTi alloy via laser beam manipulation. Int J Mach Tools Manuf. 2024; 202:104210. doi: 10.1016/j.ijmachtools.2024.104210

[21] Hariharan A, Ackermann M, Koss S, et al. High‐Speed 3D Printing Coupled with Machine Learning to Accelerate Alloy Development for Additive Manufacturing. Adv Sci. 2025; 12(17):2414880. doi: 10.1002/advs.202414880

[22] Wei HL, Mukherjee T, Zhang W, et al. Mechanistic models for additive manufacturing of metallic components. Prog Mater Sci. 2021; 116:100703. doi: 10.1016/j.pmatsci.2020.100703

[23] DebRoy T, Mukherjee T, Wei HL, Elmer JW, Milewski JO. Metallurgy, mechanistic models and machine learning in metal printing. Nat Rev Mater. 2021; 6(1):48-68. doi: 10.1038/s41578-020-00236-1

[24] Du Y, Mukherjee T, Li R, et al. A review of deep learning in metal additive manufacturing: Impact on process, structure, and properties. Prog Mater Sci. 2026; 157:101587. doi: 10.1016/j.pmatsci.2025.101587

[25] Faegh M, Ghungrad S, Oliveira JP, Rao P, Haghighi A. A review on physics-informed machine learning for process-structure-property modeling in additive manufacturing. J Manuf Process. 2025; 133:524-555. doi: 10.1016/j.jmapro.2024.11.066

[26] Faegh M, Sanvelly RR, Arabpoor R, Rao P, Mukherjee T, Haghighi A. Physics-informed neural networks for thermal modeling transferable across paths, print parameters, and beam profiles. Addit Manuf. 2026; 116:105060. doi: 10.1016/j.addma.2025.105060

[27] Kyaw AH, Gupta R, Shah D, et al. Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models. arXiv. Preprint Posted online November 4, 2025. doi: 10.48550/arXiv.2511.02162

[28] Pak P, Barati Farimani A. AdditiveLLM: Large language models predict defects in metals additive manufacturing. Addit Manuf Lett. 2025; 14:100292. doi: 10.1016/j.addlet.2025.100292

[29] Zheng Q, Zhang J, Gockel J, Wakin MB, Brice C, Zhang X. QA-VLM: Providing human-interpretable quality assessment for wire-feed laser additive manufacturing parts with vision language models. J Manuf Process. 2026; 160:611-623. doi: 10.1016/j.jmapro.2026.01.071

[30] Jadhav Y, Pak P, Barati Farimani A. LLM-3D print: Large Language Models to monitor and control 3D printing. Addit Manuf. 2025; 114:105027. doi: 10.1016/j.addma.2025.105027

[31] Bougzime O, Cruz C, Zhou K, Qi HJ, Demoly F. Structuring scientific knowledge for smart materials and 4D printing: An ontology enrichment framework using retrieval-augmented multimodal large language models. Comput Ind. 2026; 180:104522. doi: 10.1016/j.compind.2026.104522

[32] Liang CX, Tian P, Yin CH, et al. A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks. Computation. 2026; 14(6):125. doi: 10.3390/computation14060125

[33] Li J, Shi D, Zhang Z, Bauernhansl T. Data-driven meets knowledge-driven: an LLM-agent framework for quality control in metal additive manufacturing. J Ind Inf Integr. 2026; 53:101182. doi: 10.1016/j.jii.2026.101182

[34] Michalski RS, Carbonell JG, Mitchell TM eds. Machine Learning: An Artificial Intelligence Approach. Berlin, Germany: Springer; 1983. doi: 10.1007/978-3-662-12405-5

[35] Khanghah KN, Chen Z, Romeo L, et al. Zero-Shot Anomaly Detection in Laser Powder Bed Fusion Using Multimodal Retrieval-Augmented Generation and Large Language Models. J Mech Des. 2025; 148(7):072001. doi: 10.1115/1.4070585

[36] Zeng Z, Li Y, Yu S, Liu W, Zhang H, Peng S. Agentic multimodal LLM-augmented expert system with physics-aware dual-index RAG for metal additive manufacturing. SSRN. Preprint Posted online February 3, 2026. doi: 10.2139/ssrn.6170301

[37] Margadji C, Pattinson SW.Hybrid reasoning for perception, explanation, and autonomous action in manufacturing. Nat Commun. 2026; 17(1):6589. doi: 10.1038/s41467-026-72378-9

[38] Eslaminia A, Cai C, Smith C, et al. LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing. arXiv. Preprint Posted online May 5, 2026. doi: 10.48550/arXiv.2605.03328

[39] Wu G. Defect Detection in Fused Filament Fabrication With Artificial Intelligence. Master’s thesis. RMIT University; 2025. doi: 10.25439/rmt.29207987

[40] Qian J. A Vision-language model as embodied manufacturing agent. Dissertation. University of Cambridge; 2024. Accessed September 24, 2026. ac.uk/files/2023-2024/qian_a-vision-language_2024.pdf

[41] Fang Q, Xiong G, Wang F, Shen Z, Dong X, Wang FY. Large Language Models as Few-Shot Defect Detectors for Additive Manufacturing. In: 2024 China Automation Congress (CAC). Qingdao, China; 2024:6900-6905. doi: 10.1109/cac63892.2024.10865554

[42] Wang XQ, Jin Z, Zheng B, Gu GX. Transformer-based approach for printing quality recognition in fused filament fabrication. npj Adv Manuf. 2025; 2(1):15. doi: 10.1038/s44334-025-00025-0

[43] Zolfagharian A, Jin L, Ge Q, et al. Roadmap on Artificial Intelligence‐Augmented Additive Manufacturing. Adv Intell Syst. 2026; 8(4):e202500484. doi: 10.1002/aisy.202500484

[44] Giri S, Zheng Q, Zhang X, Liu S. Interactive multimodal quality assessment in laser powder bed fusion using vision-large language models. J Manuf Process. 2026; 174:1168-1181. doi: 10.1016/j.jmapro.2026.08.008

[45] Wei W, Li Y, Wu H, et al. Gcs-Unet: A lightweight attention network for coaxial melt pool monitoring in laser powder bed fusion. Smart Mater Manuf. 2025; 3:100094. doi: 10.1016/j.smmf.2025.100094

[46] Zhu T, Chen W. Mechanical behaviour of additively manufactured metals. Nat Mater. 2026; 25(3):373-385. doi: 10.1038/s41563-025-02459-5

[47] Liu H, Yu H, Guo C, et al. Review on Fatigue of Additive Manufactured Metallic Alloys: Microstructure, Performance, Enhancement, and Assessment Methods. Adv Mater. 2023; 36(17):2306570. doi: 10.1002/adma.202306570

[48] Quan W, Rosen DW, Song B. A review of Generative Artificial Intelligence for additive manufacturing: Bridging design, process monitoring, and beyond. J Manuf Syst. 2026; 86:393-416. doi: 10.1016/j.jmsy.2026.03.013

[49] Leng J, Wang J, Zhou L, et al. A review of multi-modal deep learning towards agentic smart manufacturing. Adv Eng Inform. 2026; 70:104117. doi: 10.1016/j.aei.2025.104117

[50] Tuli NT, Dutta S, Mukherjee T. Specific heat and thermal conductivity variations from absolute zero to solidus temperature for standard stainless steels and aluminum alloys. Mater Res Express. 2026; 13(8):086501. doi: 10.1088/2053-1591/ae5d08

[51] Dong Z, Lu Z, Yang Y. Fine-tuning a large language model for automating computational fluid dynamics simulations. Theor Appl Mech Lett. 2025; 15(3):100594. doi: 10.1016/j.taml.2025.100594

[52] Holt S, Luyten MR, Berthon A, van der Schaar M. G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration. arXiv. Preprint Posted online June 10, 2025. doi: 10.48550/arXiv.2506.09272

[53] Ma P, Wang TH, Guo M, et al. LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery. arXiv. Preprint Posted online May 16, 2024. doi: 10.48550/ARXIV.2405.09783

[54] Deotale R, Srinivasan A, Golestanian M, et al. ALL-FEM: Agentic Large Language Models fine-tuned for finite element methods. Comput Methods Appl Mech Eng. 2026; 457:118985. doi: 10.1016/j.cma.2026.118985

[55] Liu J, Wang N. AutoSurrogate: An LLM-driven multi-agent framework for autonomous construction of deep learning surrogate models in subsurface flow. Adv Eng Inform. 2026; 76:105058. doi: 10.1016/j.aei.2026.105058

[56] Tang G, Paulson N. An LLM-Agentic Workflow for Data-Driven Modeling: From Toy Image Reconstruction to Thermodynamic Modeling. Res Sq. Preprint Posted online January 13, 2026. doi: 10.21203/rs.3.rs-8574739/v1

[57] Liu Z, Chai Y, Li J. Toward Automated Simulation Research Workflow through LLM Prompt Engineering Design. J Chem Inf Model. 2025; 65(1):114-124. doi: 10.1021/acs.jcim.4c01653

[58] Lee K, Yu Z, Lai ZH, et al. Derivation of physical equations for high-speed laser welding using large language models. Int J Mach Tools Manuf. 2025; 211:104320. doi: 10.1016/j.ijmachtools.2025.104320

[59] Devadas RM, T S. Quantum machine learning: A comprehensive review of integrating AI with quantum computing for computational advancements. MethodsX. 2025; 14:103318. doi: 10.1016/j.mex.2025.103318

[60] Nausheen F, Ahmed K, Khan MI, Riaz F. Quantum Natural Language Processing: A Comprehensive Review of Models, Methods, and Applications. arXiv. Preprint Posted online April 14, 2025. doi: 10.48550/arXiv.2504.09909

[61] Arjomandi M, Motley J, Ngo Q, Anees Y, Afzal MA, Mukherjee T. A Review on In-Situ Monitoring in Wire Arc Additive Manufacturing: Technologies, Applications, Challenges, and Needs. Machines. 2025; 14(1):19. doi: 10.3390/machines14010019

[62] Arjomandi M, Mukherjee T. A review of applications of collaborative robot in welding and additive manufacturing. Robot Comput-Integr Manuf. 2026; 100:103256. doi: 10.1016/j.rcim.2026.103256

[63] Choi E, Sul J, Kim JE, et al. Quantum machine learning for additive manufacturing process monitoring. Manuf Lett. 2024; 41:1415-1422. doi: 10.1016/j.mfglet.2024.09.168

[64] Rodríguez-Díaz F, Gutiérrez-Avilés D, Troncoso A, Martínez-Álvarez F. A Survey of Quantum Machine Learning: Foundations, Algorithms, Frameworks, Data and Applications. ACM Comput Surv. 2025; 58(4):91. doi: 10.1145/3764582

[65] Cappelli L, Succi S, Lăcătuş M, Zecchi AA, Roggero A. Schrödinger-Navier-Stokes equation for the quantum simulation of Navier-Stokes flows. Quantum Sci Technol. 2026; 11(3):035079. doi: 10.1088/2058-9565/ae9339

[66] Gaitan F. Finding flows of a Navier-Stokes fluid through quantum computing. npj Quantum Inf. 2020; 6(1):61. doi: 10.1038/s41534-020-00291-0

[67] Gaitan F. Finding Solutions of the Navier‐Stokes Equations through Quantum Computing-Recent Progress, a Generalization, and Next Steps Forward. Adv Quantum Tech. 2021; 4(10):2100055. doi: 10.1002/qute.202100055

[68] Bożejko W, Trotskyi S, Uchroński M, Wodecki M. Optimizing two-machine scheduling in flexible manufacturing systems using autonomous AI and quantum computing. Neurocomputing. 2026; 664:132067. doi: 10.1016/j.neucom.2025.132067

[69] Flores-Garrigós C, Dev G, Falkenthal M, et al. Quantum combinatorial reasoning for large language models. Phys Rev Res. 2026; 8(3):033070. doi: 10.1103/kk5d-tb9b

[70] Closser DC, Kabala ZJ. Pushing the Limits of Large Language Models in Quantum Operations. Quantum Rep. 2026; 8(1):7. doi: 10.3390/quantum8010007

[71] Chen M, Cheng J, Li P, Wang H, Chen T, Liu J. Symbolic analysis of Grover search algorithm via Chain-of-Thought reasoning and quantum-native tokenization. npj Quantum Inf. 2026; 12(1):48. doi: 10.1038/s41534-026-01195-1

[72] Sakka K, Mizukami W, Mitarai K. An LLM System for Autonomous Variational Quantum Circuit Design. arXiv. Preprint Posted online June 11, 2026. doi: 10.48550/ARXIV.2606.13380

[73] Zhao Y, Jiang B, Lu M, Wang X, Tang J. MQAdapter: Multi-Modal Quantum Adapter for Coarse-to-Fine VLM Fine-tuning. arXiv. Preprint Posted online July 14, 2026. doi: 10.48550/ARXIV.2607.12418

[74] Braz SL, Leite JPRR. Quantum assistant: Specialization of multimodal vision-language models for quantum computing. Expert Syst Appl. 2027; 333:133931. doi: 10.1016/j.eswa.2026.133931

[75] Hawashin H, Abbaszadeh M, Joseph N, Pearson B, Lewis M, Sadrzadeh M. Compositional Concept Generalization with Variational Quantum Circuits. In: 2025 IEEE International Conference on Quantum Artificial Intelligence (QAI). Naples, Italy; 2025:34-40. doi: 10.1109/qai63978.2025.00013

[76] Jern L, Uotila V, Yu C, Zhao B. Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimization. In: 2025 IEEE International Conference on Quantum Computing and Engineering (QCE). Albuquerque, NM, USA; 2025:1621-1632. doi: 10.1109/qce65121.2025.00179

[77] Chen Z, Guo F, Chen Z, Zuo L, Liu Y. PCBClip: Vision-Language Defect Detection Model for Low-Sample Inspection Systems. IEEE Trans Pattern Anal Mach Intell. 2026; 48(10):13406-13423. doi: 10.1109/tpami.2026.3711750

[78] Nguyen HV, Park H, Yoo N, Yang J. Resource-Efficient Adaptation of Large Vision-Language Models for Multimodal Defect Inspection in LNG Tank Manufacturing. Int J Adv Manuf Technol. 2026; 144(7-8):5135-5152. doi: 10.1007/s00170-026-17818-y

[79] Zhang W, Zhang C, Gu C, et al. Hallucination in Large Language Models:From Mechanistic Understanding to Novel Control Frameworks. In: 2024 7th International Conference on Universal Village (UV). Boston, MA, USA; 2024:1-36. doi: 10.1109/uv63228.2024.11189226

[80] Chandrasekhar A, Chan J, Ogoke F, Ajenifujah O, Barati Farimani A. AMGPT: A large language model for contextual querying in additive manufacturing. Addit Manuf Lett. 2024; 11:100232. doi: 10.1016/j.addlet.2024.100232

[81] Sagor SI, Haghighi T, Rahatuzzaman M, et al. Domain adaptation of large language models for additive manufacturing using retrieval-augmented generation and fine-tuning. Front Manuf Technol. 2026; 6:1875357. doi: 10.3389/fmtec.2026.1875357

[82] Dandigam R, Patel M, Pareek CS, Faysal SM, Alam GT, Siam MA. Human-in-the-Loop Learning for Improving Language Model Reliability. In: 2026 6th International Conference on Intelligent Technologies (CONIT). Belgavi, India; 2026:1-8. doi: 10.1109/conit69683.2026.11620666

[83] Yang W, Some L, Bain M, Kang B. A comprehensive survey on integrating large language models with knowledge-based methods. Knowl-Based Syst. 2025; 318:113503. doi: 10.1016/j.knosys.2025.113503

[84] Khvatskii G, Lee YS, Angst C, Gibbs M, Landers R, Chawla NV. Do multimodal large language models understand welding? Inf Fusion. 2025; 120:103121. doi: 10.1016/j.inffus.2025.103121

[85] Shorinwa O, Mei Z, Lidard J, Ren AZ, Majumdar A. A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions. ACM Comput Surv. 2025; 58(3):63. doi: 10.1145/3744238