EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Optimizing RAG-Assisted Code Generation for Cloud-Native ML Pipelines Through Dynamic Context Window Management

David Kim

Journal of Computing and Electronic Information Management · 29.06.2026 · 21 (3) · 1-7

DOI: 10.54097/53p2w481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing and Electronic Information Management, online erschienen am 29.06.2026. Verfasst von David Kim. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proliferation of cloud-native machine learning (ML) infrastructure has created significant demand for automated code generation systems capable of producing syntactically and semantically correct pipeline configurations. Retrieval-Augmented Generation (RAG) offers a principled mechanism for grounding large language model (LMM) inference in dynamically retrieved contextual knowledge; however, naive implementations suffer from context window saturation and relevance dilution when applied to complex multi-component ML pipeline repositories. This paper proposes a Dynamic Context Window Management (DCWM) framework integrated within a RAG-assisted code generation system targeting cloud-native ML workflows. The framework introduces a multi-stage retrieval mechanism coupled with an adaptive context compression module that selectively ranks and prioritizes retrieved code artifacts through attention-weighted scoring. An abstract syntax tree guided generation pipeline further enforces syntactic validity of produced pipeline code. Empirical evaluation across three benchmark task categories demonstrates a 23.7% improvement in pass@1 accuracy and a 19.4% reduction in hallucinated API calls relative to static context window baselines. These findings establish dynamic context management as a first-class design consideration in RAG-enhanced code generation for cloud-native environments.

Zitieren

APA

Kim, D. (2026). Optimizing RAG-Assisted Code Generation for Cloud-Native ML Pipelines Through Dynamic Context Window Management. Journal of Computing and Electronic Information Management, 21(3), 1-7. https://doi.org/10.54097/53p2w481

Vancouver

Kim D. Optimizing RAG-Assisted Code Generation for Cloud-Native ML Pipelines Through Dynamic Context Window Management. Journal of Computing and Electronic Information Management. 2026;21(3):1-7. doi:10.54097/53p2w481

BibTeX
@article{Kim2026,
  author = {Kim, David},
  title = {Optimizing RAG-Assisted Code Generation for Cloud-Native ML Pipelines Through Dynamic Context Window Management},
  journal = {Journal of Computing and Electronic Information Management},
  year = {2026},
  volume = {21},
  number = {3},
  pages = {1--7},
  doi = {10.54097/53p2w481}
}
Kostenlos starten →