Retrieval-augmented generation (RAG) enhances large language models (LLMs) for domain-specific question-answering (QA) tasks by leveraging external knowledge sources. However, traditional RAG systems primarily focus on relevance-based retrieval and often struggle with redundancy, especially when reasoning requires connecting information from multiple sources. This paper introduces Vendi-RAG, a framework based on an iterative process that jointly optimizes retrieval diversity and answer quality. This joint optimization leads to significantly higher accuracy for multi-hop QA tasks. Vendi-RAG levResearch goal: Does the Tree of Reviews iterative retrieval method improve robustness to irrelevant context in multi-hop QA compared to single-step retrieval on the 2WikiMultihop dataset, measured by F1 score and precision?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.2/10.