Automated Prompt Optimization in Software Engineering: A Survey and Proposed Intent-Chaining Architecture
Keywords:
Chain-of-Thought, Few-Shot Prompting, Intent Extraction, LangChain, Large Language Models, Prompt Engineering, Software EngineeringAbstract
Prompt engineering has emerged as a critical discipline for effectively utilizing Large Language Models (LLMs) across software engineering tasks, including code generation, debugging, documentation, and domain-specific language development. However, the rapid proliferation of prompting techniques has created a fragmented landscape, making it challenging for practitioners to identify suitable approaches for their specific requirements. This survey provides a comprehensive review and comparative analysis of contemporary prompt engineering methodologies in software engineering, examining eight representative studies across three key dimensions: prompt optimization techniques, evaluation frameworks, and domain-specific applications. They systematically analyze each approach based on its methodology, key contributions, and inherent limitations. Our analysis reveals several persistent challenges, including domain specificity, lack of interpretable evaluation feedback, reliance on single datasets, and fragmentation of complementary techniques. Based on these findings, critical research gaps were identified, and an integrated framework was proposed that combines intent extraction, few-shot prompting, and prompt chaining in a unified modular pipeline designed to overcome the limitations identified in existing approaches. This paper serves as both a comprehensive reference for researchers and practitioners in prompt engineering and a foundation for developing more accessible, interpretable, and generalizable LLM interaction tools for software engineering applications.
References
A. F. Subahi, “Prompt Engineering for Advancing Software Engineering: Using Generative Language Models in the Development of Domain-Specific Languages,” IEEE Access, vol. 14, pp. 22834–22850, 2026.
M. Rizqullah and E. Albassam, “Model-Agnostic Empirical Evaluation of Test-Driven Prompt Engineering on Improving Accuracy and Efficiency in Large Language Models Python Code Generation,” IEEE Access, vol. 14, pp. 22801–22821, 2026.
M. Hong, E. Lee, S. Park, and J. Kim, "PEEM: Prompt engineering evaluation metrics for interpretable joint evaluation of prompts and responses in LLMs," IEEE Access, vol. 14, pp. 1-17, 2026.
W.-C. Chen and S.-Y. Chen, "TIPS: A prompt engineering framework for code classification and generation on resource-constrained systems," IEEE Access, vol. 14, pp. 1-13, 2026.
L. J. Laki and Z. G. Yang, “Improving Machine Translation Capabilities by Fine-Tuning Large Language Models and Prompt Engineering with Domain-Specific Data,” 2024 IEEE 3rd Conference on Information Technology and Data Science (CITDS), Aug. 2024, pp. 1–5.
L. A. Loss and Pratikkumar Dhuvad, “An LLM-Based Genetic Algorithm for Prompt Engineering,” Proceedings of the Genetic and Evolutionary Computation Conference Companion, July 2025, pp. 527–530.
A. Jayakody, O. Abeyrathne, T. Perera, S. Kavindhu, and Y. Namarathna, “Personalizing University Support: Benchmarking Lightweight RAG Systems Against Commercial LLMs in Higher Education Administration,” 2026 6th International Conference on Advanced Research in Computing (ICARC), Feb. 2026, pp. 1–5.
K. I. Roumeliotis, N. D. Tselikas, and D. K. Nasiopoulos, “When Multimodal Large Language Models Meet Computer Vision: Progressive GPT Fine-Tuning and Stress Testing,” IEEE Access, vol. 13, pp. 106155–106174, 2025.
N. Agade, S. Hajare, D. Timande, J. Abhvankar, N. Pardhi, and N. U. Sambhe, “Prompt Engineering for Large Language Models: Zero-shot, Few-shot, and Beyond,” 2025 3rd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIHEI), Nov. 2025, pp. 1–6.
S. Kotani, H. Mori, and N. Moghaddam Charkari, “Danger estimation of the Robotic Travel Aid (RoTA) at intersection,” Robotics and Autonomous Systems, vol. 18, no. 1–2, pp. 235–242, July 1996.
M. Son and S. Lee, “Performance Analysis of Prompt-Engineering Techniques for Large Language Model,” 2025 IEEE International Conference on Consumer Electronics (ICCE), Jan. 2025, pp. 1–5.
P. Haindl, P. Kieseberg, and O. Eigner, “Designing an LLM-Augmented Course for Secure Coding Using a Structured Learning Design Model and Prompt Patterns,” Oct. 2025.
P. Sahoo, A. K. Singh, S. Saha, V. Jain, S. Mondal, and A. Chadha, “A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications,” arXiv (Cornell University), Feb. 2024.
N. S. Teja, K. Kumar, and M. Malarvel, “Multilingual Text Enhancer (MLTE) – A LLaMA2 based Model for Prompt Generation,” 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), June 2024, pp. 895–900.
T. Kojima, S. Gu, M. Reid, Y. Matsuo, and Yusuke Iwasawa, “Large Language Models are Zero-Shot Reasoners,” arXiv (Cornell University), May 2022.
