Knowledge Retrieval Architectures for AI-Assisted Software Development: From Static Context to Autonomous Development Agents
DOI:
https://doi.org/10.64552/wipiec.v12i2.147Keywords:
Knowledge Retrieval, Large Language Models, Retrieval-Augmented Generation, Agentic RAG, Graph RAG, AI-Assisted Software Development, AI SDLCAbstract
The integration of Large Language Models (LLMs) into software development workflows has fundamentally transformed how developers interact with knowledge repositories, codebases, and documentation. However, traditional knowledge retrieval mechanisms face significant challenges when applied to the dynamic, multi-modal, and contextually-rich environment of software engineering. This survey provides a comprehensive analysis of knowledge retrieval architectures specifically designed for AI-assisted software development, examining the evolution from static context provision to autonomous development agents. Building upon this systematic examination, the paper delineates critical research directions that advance the theoretical and practical foundations of AI-assisted software development.
References
M. Muraszkiewicz and R. Nowak (eds.), Sztuczna inteligencja dla inżynierów - metody ogólne. Warsaw, 2022 (in Polish).
M. Muraszkiewicz and R. Nowak (eds.), Sztuczna inteligencja dla inżynierów - istotne obszary i zastosowania. Warsaw, 2023 (in Polish).
J. White et al., “A prompt pattern catalog to enhance prompt engineering with ChatGPT,” in PLoP ’23, Article 5, pp. 1–31, 2023.
L. Reynolds and K. McDonell, “Prompt programming for large language models: beyond the few-shot paradigm,” in CHI EA ’21, Article 314, pp. 1–7, 2021.
T. Brown et al., “Language models are few-shot learners,” in NIPS’20, Article 159, pp. 1877–1901, 2020.
J. Wei et al., “Chain-of-thought prompting elicits reasoning in large language models,” in NIPS’22, Article 1800, pp. 24824–24837, 2022.
P. Lewis et al., “Retrieval-augmented generation for knowledge-intensive NLP tasks,” in NIPS’20, Article 793, pp. 9459–9474, 2020.
Y. Gao et al., “Retrieval-augmented generation for large language models: a survey,” arXiv:2312.10997, 2023.
D. Edge et al., “From local to global: a Graph RAG approach to query-focused summarization,” arXiv:2404.16130, 2024.
Google Gemini Team, “Gemini 1.5: unlocking multimodal understanding across millions of tokens of context,” arXiv:2403.05530, 2024.
S. Krishna et al., “Fact, fetch, and reason: a unified evaluation of retrieval-augmented generation,” in Proc. NAACL-HLT, vol. 1, 2025.
Q. Wu et al., “AutoGen: enabling next-gen LLM applications via multi-agent conversation,” in COLM, Philadelphia, 2024.
T. Guo et al., “Large language model based multi-agents: a survey of progress and challenges,” in IJCAI ’24, Article 890, pp. 8048–8057, 2024.
Z. Xi et al., “The rise and potential of large language model based agents: a survey,” Sci. China Inf. Sci., vol. 68, 121101, 2025.
A. M. Dakhel et al., “GitHub Copilot AI pair programmer: asset or liability?” J. Syst. Softw., vol. 203, 2023.
V. Viswanadhapalli, “AI-augmented software development: enhancing code quality and developer productivity using large language models,” IJNRD, vol. 9, no. 8, pp. e382–e396, 2024.
N. S. Shashidhara, “AI in software engineering - how intelligent systems are changing the software development process,” EJCSIT, vol. 13, no. 29, pp. 28–39, 2025.
A. Gu et al., “Challenges and paths towards AI for software engineering,” arXiv:2503.22625, 2025.
B. Gutierrez et al., “From RAG to memory: non-parametric continual learning for large language model,” in ICML, PMLR 267, pp. 21497–21515, 2025.
R. W. Hamming, Introduction to Applied Numerical Analysis. New York: Dover, 1989.
Interesting Engineering, “What’s the biggest software package by lines of code?” 2021. [Online]. Available: https://interestingengineering.com/lists/whats-the-biggest-software-package-by-lines-of-code
FAISS Documentation. [Online]. Available: https://faiss.ai/index.html
Neo4j Documentation. [Online]. Available: https://neo4j.com/docs/
The Cambridge Handbook of Artificial Intelligence. Cambridge: Cambridge University Press, 2014.
RAGAS Documentation. [Online]. Available: https://docs.ragas.io/en/stable/
European Parliament, “The impact of the General Data Protection Regulation (GDPR) on artificial intelligence,” 2020.
Regulation (EU) 2024/1689 (Artificial Intelligence Act), 2024. [Online]. Available: https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng
E. Alor et al., “Evaluating the use of LLMs for documentation to code traceability,” arXiv:2506.16440, 2025.
G. Flouris et al., “Ontology change: classification and survey,” The Knowledge Engineering Review, vol. 23, no. 2, Cambridge University Press, 2008.
B. Kitchenham, “Procedures for performing systematic reviews,” Joint Technical Report, Software Engineering Group, Dept. of Computer Science, Keele University, 2004.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Norbert Fijałek, Ilona Bluemke, Piotr Gawrysiak
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
License Terms:
Except where otherwise noted, content on this website is lincesed under a Creative Commons Attribution Non-Commercial License (CC BY NC)
Use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes, is permitted.
Copyright to any article published by WiPiEC retained by the author(s). Authors grant WiPiEC Journal a license to publish the article and identify itself as the original publisher. Authors also grant any third party the right to use the article freely as long as it is not used for commercial purposes and its original authors, citation details, and publisher are identified, in accordance with CC BY NC license. Fore more information on license terms, click here.