A study of Raw-RAG, a naive retrieval-augmented generation baseline using dense retrieval and reranking, finds that simple RAG is stronger than expected relative to complex agentic memory systems that rely on mutation, structural organization or learned retrieval strategies for long-term conversation understanding. The work questions whether that added complexity is always necessary.
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations. Is this complexity always necessary? We study Raw-RAG, a naive RAG baseline using dense retrieval and rera
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.