Replace black-box top-K retrieval with interpretable agentic document navigation: 58.8% vs 15.7% on financial documents

arXiv 2608.06305·medium signalXBlueskyLinkedInCopy link

READ swaps dense top-K retrieval for deterministic agentic operations that navigate document structure directly, answering 58.8% of financial document questions against 15.7% for dense retrieval (p=2×10⁻⁵); even tuned baselines only reached 35.3%. The gain comes from treating retrieval as navigation over known structure rather than similarity search over chunks. For anyone whose RAG stack underperforms on long structured documents, this is the strongest recent argument that the embedding model is not the bottleneck — the retrieval paradigm is.