The rapid evolution of large language models (LLMs) has catalyzed transformative changes across artificial intelligence applications, from natural language processing and code optimization to cybersecurity and edge intelligence. Despite their unprecedented capabilities, LLMs present critical challenges in efficiency, security, trustworthiness, and environmental impact. This research systematically examines contemporary LLM architectures, deployment strategies, and optimization techniques, emphasizing firmware-level and energy-efficient solutions. The study integrates a comprehensive survey of LLM applications in software engineering, phishing detection, SoC security, and malicious insider threat mitigation. Methodological insights include detailed analyses of instruction tuning, code generation optimization, and search-based LLM approaches for enhanced computational performance. Results highlight the trade-offs between model accuracy, latency, and energy consumption, revealing that firmware-level optimization and heuristic-based inference strategies significantly improve LLM performance while reducing operational costs. Discussion addresses the limitations of current architectures, potential risks of autonomous vulnerability exploitation, and environmental concerns associated with large-scale deployments. The study concludes with actionable recommendations for designing next-generation LLMs that balance computational efficiency, robustness, and ecological sustainability, while fostering secure and reliable AI-driven systems.

Large language models, LLM optimization, edge intelligence, code generation

O. Friha, et al., “LLM-based edge intelligence: A comprehensive survey on architectures, applications, security and trustworthiness,” IEEE Open J. Commun. Soc., 2024.

S. Jamal, H. Wimmer, and I. H. Sarker, “An improved transformer-based model for detecting phishing, spam and ham emails: A large language model approach,” Security Privacy, p. e402, 2024. https://doi.org/10.1002/spy2.402

W. X. Zhao, et al., “A survey of large language models,” arXiv preprint arXiv:2303.18223, 2023.

F. R. Alzaabi and A. Mehmood, “A review of recent advances, challenges, and opportunities in malicious insider threat detection using machine learning methods,” IEEE Access, vol. 12, pp. 30907–30927, 2024.

M. A. K. Raiaan, et al., “A review on large language models: Architectures, applications, taxonomies, open issues and challenges,” IEEE Access, vol. 12, pp. 26839–26874, 2024.

R. Fang, et al., “LLM agents can autonomously exploit one-day vulnerabilities,” arXiv preprint arXiv:2404.08144, 2024.

Y. Chang, et al., “A survey on evaluation of large language models,” ACM Trans. Intell. Syst. Technol., 2023.

D. Saha, et al., “LLM for SoC security: A paradigm shift,” arXiv preprint arXiv:2310.06046, 2023.

B. Min, et al., “Recent advances in natural language processing via large pre-trained language models: A survey,” ACM Comput. Surv., vol. 56, no. 2, pp. 1–40, 2023.

S. Zhang, et al., “Instruction tuning for large language models: A survey,” arXiv preprint arXiv:2308.10792, 2023.

Fan, et al., “Large language models for software engineering: Survey and open problems,” arXiv preprint arXiv:2310.03533, 2023.

Berthelot, E. Caron, M. Jay, and L. Lefevre, “Estimating the environmental impact of Generative-AI services using an LCA-based methodology,” Procedia CIRP, vol. 122, pp. 707–712, 2024.

R. Chandra, “Reducing latency and enhancing accuracy in LLM inference through firmware-level optimization,” International Journal of Signal Processing, Embedded Systems and VLSI Design, 5(2), 26-36, 2025. https://doi.org/10.55640/ijvsli-05-02-02

T. Coignion, C. Quinton, and R. Rouvoy, “Green My LLM: Studying the key factors affecting the energy consumption of code assistants,” arXiv, Nov. 2024.

J. Liu, S. Xie, J. Wang, Y. Wei, Y. Ding, and L. Zhang, “Evaluating Language Models for Efficient Code Generation,” arXiv, Aug. 2024.

S. Garg, R. Z. Moghaddam, and N. Sundaresan, “RAPGen An Approach for Fixing Code Inefficiencies in Zero-Shot,” arXiv, Jul. 2024.

S. Gao, C. Gao, W. Gu, and M. Lyu, “Search-Based LLMs for Code Optimization,” arXiv, Aug. 2024.