BM25

DecisionRAG is a novel retrieval framework that replaces traditional lexical or dense matching with hierarchical navigation using decision models. By evaluating candidates in a shared context without generating tokens, it achieves superior accuracy and much lower latency than existing agentic or reranking methods.

This research investigates how different RAG architectures scale in accuracy and cost as document corpora expand from thousands to hundreds of thousands of files. The findings reveal a performance crossover where BM25 becomes the most effective and cost-efficient method at large scales.

This technical comparison evaluates various state-of-the-art frameworks designed to implement long-term, scalable memory for AI agents. It categorizes research based on how information is represented, stored, extracted, retrieved, and maintained within LLM architectures.