Architecture Matters: Comparing RAG Systems under Knowledge Base Poisoning

Samuel Korn

Abstract

Retrieval-Augmented Generation (RAG) systems are vulnerable to knowledge base poisoning, yet existing attacks have been evaluated almost exclusively against vanilla retrieve-then-generate pipelines. Architectures designed to handle conflicting retrieved information - multi-agent debate, agentic retrieval, recursive language models - remain untested against adversarially optimized contradictions. We evaluate four RAG architectures (vanilla RAG, agentic RAG, MADAM-RAG, and Recursive Language Model

Categories

Cite This Resource

@article{llmsec202600137,
  title = {Architecture Matters: Comparing RAG Systems under Knowledge Base Poisoning},
  author = {Samuel Korn},
  year = {2026},
  url = {https://arxiv.org/abs/2605.05632},
}