Architecture and Workload as Primary Sources of Error in RAG and Agentic AI Systems: Summary of Two Years of ☸️SAIMSARA Development
Web3 Journal: ML in Health Science · 2025
DOI: 10.62487/5a1m5ara ↗Kurz gefasst
Fachartikel in der Zeitschrift Web3 Journal: ML in Health Science, 2025. Verfasst von SAIMSARA. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Errors in Retrieval-Augmented Generation (RAG) and agentic AI systems are commonly attributed to limitations of large language models. Based on two years of developing ☸️SAIMSARA, a large-scale agentic AI system for medical scientific article review, this editorial argues that most failures arise instead from architectural design and workload allocation. Key pitfalls include prompt overload, excessive batch size, oversized input items, and the use of speed-optimized models in multi-stage workflows. Practical mitigation strategies are outlined, emphasizing the importance of aligning prompt complexity, batch structure, and input size with model capacity. The findings highlight that robustness in RAG and agentic AI systems is primarily a systems engineering challenge rather than a model selection problem.
Zitieren
APA
SAIMSARA (2025). Architecture and Workload as Primary Sources of Error in RAG and Agentic AI Systems: Summary of Two Years of ☸️SAIMSARA Development. Web3 Journal: ML in Health Science. https://doi.org/10.62487/5a1m5ara
Vancouver
SAIMSARA. Architecture and Workload as Primary Sources of Error in RAG and Agentic AI Systems: Summary of Two Years of ☸️SAIMSARA Development. Web3 Journal: ML in Health Science. 2025. doi:10.62487/5a1m5ara
BibTeX
@article{SAIMSARA2025,
author = {SAIMSARA},
title = {Architecture and Workload as Primary Sources of Error in RAG and Agentic AI Systems: Summary of Two Years of ☸️SAIMSARA Development},
journal = {Web3 Journal: ML in Health Science},
year = {2025},
doi = {10.62487/5a1m5ara}
}
EUVIMED