Recent advances in Large Language Models (LLMs) have transformed natural language processing, yet their potential in engineering design and product development is only beginning to be explored. This paper presents a systematic literature review (SLR) focused on identifying current research trends, application domains, and technical challenges associated with LLMs in the context of product development. Adhering to established SLR guidelines, we searched multiple scientific to capture relevant studies published within the last five years.

Our synthesis of the selected publications revealed a growing interest in leveraging LLMs for various tasks such as conceptual design, requirements management, and knowledge retrieval. However, the literature also highlights concerns regarding data quality, interpretability, and the domain-specific adaptation of pre-trained models. To address these challenges, we evaluated a range of open-source and commercial LLM frameworks—most notably Hugging Face Transformers, OpenAI APIs, and proprietary cloud-based solutions—and compared them based on criteria such as performance, deployment feasibility, and integration into engineering workflows.

The findings underscore the need for specialized toolchains that consider engineering constraints, privacy requirements, and the complexity of technical documentation. Our review culminates in a set of practical recommendations for researchers and practitioners seeking to adopt or further develop LLM-based solutions in design engineering. By outlining existing gaps and potential avenues for advancement, this work contributes to a more holistic understanding of how LLMs can be systematically integrated into product development processes.