{"type":"link","version":"1.0","title":"Multi-hop RAG is bottlenecked by LLM call count, not retrieval — delegate intermediate reasoning to fine-tuned models","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/multihop-bottleneck-is-llm-calls","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}