We benchmarked 18 RAG pipelines against an agent loop on Google's FRAMES. The best pipeline hit 78.9%. The agent loop hit 92.7%.

Hybrid search, reranking, query decomposition, and query expansion are often treated as must-haves for good RAG. We wanted to see how much each actually helped, so we tested them. Same model, same embeddings, same documents, across all 824 multi-hop questions in FRAMES. We built 18 pipeline variants

中文全文翻译正在补齐，可先查看下方英文原文。

Hybrid search, reranking, query decomposition, and query expansion are often treated as must-haves for good RAG. We wanted to see how much each actually helped, so we tested them. Same model, same embeddings, same documents, across all 824 multi-hop questions in FRAMES. We built 18 pipeline variants