# naive rag Published articles for naive rag. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought DevFeed: [Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought]() Original publisher: [Read original article]() Author: Zhengye Bao, Shengtao Zhang, Haokai Zhang, Shiqi Lou, Muning Wen, Minnan Luo Published: 2026-10-23T04:00:00Z Content type: news Language: en Sources: [arXiv: Artificial Intelligence]() Topics: [Retrieval Augmented Generation (RAG)](), [Artificial Intelligence](), [llm-reasoning](), [Machine learning]() Tags: [agentic](), [agentic-memory](), [analysis](), [benchmark](), [coverage](), [cs-ai](), [history](), [memory](), [naive-rag](), [rag](), [raw](), [reranking]() ### AI overview Raw-RAG, which retrieves and reranks passages from unmodified conversation history for a reader LLM, ranked first among the compared memory systems in six of seven benchmark-model settings across LoCoMo, LongMemEval, MEME, and MemoryAgentBench. It exceeded the strongest compared agentic memory system by 0.13-5.53 points. The analysis attributes its competitiveness to broader coverage of needed evidence, which can offset lower utilization; that evidence includes answer values as well as relations and dependency paths needed to derive answers. Even complete access to transformed memory stores left an accuracy gap compared with raw evidence. These findings challenge the need for complex agentic memory on the evaluated tasks and establish naive RAG as an essential baseline. ### Source excerpt arXiv:2610.30755v1 Announce Type: new Abstract: 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 reranking over raw history to supply evidence to a reader LLM. Across LoCoMo, LongMemEval, MEME, and MemoryAgentBench, Raw-RAG ranks first among the compared memory systems in six of seven benchmark-model settings, outperforming the strongest compared agentic memory system by 0.13-5.53 points. We investigate why raw-history retrieval remains competitive. Evidence analysis shows that its higher coverage of necessary evidence can offset lower utilization. Useful evidence includes both answer values and the relations and dependency paths needed to derive them. Even complete access to transformed memory stores leaves an accuracy gap relative to raw evidence, highlighting the importance of preserving raw information. These findings challenge the necessity of complex agentic memory for the evaluated conversation tasks and establish naive RAG as an essential baseline. ## Spring AI Modular RAG and TypeSafe Jev: Retrieve More, Keep Only What Answers DevFeed: [Spring AI Modular RAG and TypeSafe Jev: Retrieve More, Keep Only What Answers]() Original publisher: [Read original article]() Author: tzolov Published: 2026-10-02T00:00:00Z Content type: article Language: en Sources: [Spring]() Topics: [Retrieval Augmented Generation (RAG)](), [Spring AI](), [AI Architecture](), [AI Integration Strategies]() Tags: [batch](), [boot](), [cloud](), [event-driven](), [java](), [jev](), [llm](), [microservices](), [modular](), [naive-rag](), [pdf](), [pipeline](), [rag](), [reactive](), [retrieval](), [serverless](), [spring](), [spring-ai](), [typesafe](), [web-applications]() ### AI overview The example combines Spring AI's Modular RAG pipeline with Jev to turn a chatty question into focused searches and keep retrieved passages that can answer it. `RetrievalAugmentationAdvisor` rewrites and expands the query, retrieves and deduplicates similar chunks, then applies `JevDocumentFilter` before `JevDocumentReranker`; the original question remains the input to post-processing and answer generation. In the Hurricane Milton demo, six retrieved chunks included reference entries that were topically similar but unhelpful. Jev filtered those out and kept two answer-bearing chunks, producing a response that Milton made landfall near Siesta Key on October 9, 2024, as a Category 3 hurricane. The filter preserves contradictory evidence, and both Jev stages fail open if the API is unreachable. The pipeline adds two LLM calls before retrieval and one Jev call per retrieved chunk, so the article advises measuring latency. It also notes that supplying Spring's `TaskExecutor` prevents a command-line app from hanging after output. ### Source excerpt Spring AI: RAG Doc | Jev Doc | Demo In the previous article we introduced Spring AI TypeSafe and its Jev model: typed questions in, calibrated numbers out, in a few hundred milliseconds. One row in that article's SPI table deserves its own post. JevDocumentFilter and JevDocumentReranker are DocumentPostProcessors, which means they plug straight into Spring AI's Modular RAG pipeline. This article puts the two together. Two LLM calls clean up and multiply the user's question before retrieval. Jev then judges every retrieved chunk before it reaches the prompt. The whole pipeline is one advisor builder. 💡 Demo: The complete example is the 05-1-modular-rag module. It sits next to 05-rag, the naive version, so you can diff the two. Every output quoted below is from a live run. Why Naive RAG Falls Short The classic Spring AI RAG demo is a QuestionAnswerAdvisor over a vector store. It embeds the user's text, fetches similar chunks and stuffs them into the prompt. That works on stage and gets shaky in real life, for three reasons: Users don't type search queries. They type "I'm a Florida resident and heard a lot about storms last fall. Did Milton actually make landfall in my state, and where?" Embedding that verbatim drags all the noise into the search. Similar is not the same as useful. A vector store returns chunks that are about the topic. A reference list that mentions "Hurricane Milton" five times scores high and answers nothing. Retrieved text is untrusted input. Whatever sits in your documents goes straight into the prompt, including text written to hijack the model. We will answer exactly that question over a Wikipedia PDF about Hurricane Milton, and fix each problem with one pluggable component. Modular RAG in Spring AI The RetrievalAugmentationAdvisor, from the spring-ai-rag module, implements the architecture described in Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks. From the outside it is just another advisor: it sits between you ## Four Retrieval Techniques for Improving Retrieval-Augmented Generation DevFeed: [Four Retrieval Techniques for Improving Retrieval-Augmented Generation]() Original publisher: [Read original article]() Author: Richard Gall Published: 2025-04-14T00:00:00Z Content type: article Language: en Sources: [Thoughtworks Insights]() Topics: [Retrieval Augmented Generation (RAG)](), [Large Language Model](), [Embeddings](), [Generative AI](), [Database]() Tags: [challenges](), [context](), [cost](), [data](), [database](), [embeddings](), [evaluation](), [generative-ai](), [naive-rag](), [rag](), [reliability](), [retrieval](), [techniques]() ### AI overview This article explains how retrieval-augmented generation improves the reliability and accuracy of generative AI, while discussing limitations involving context, cost, complex queries, and large datasets. It introduces several retrieval approaches, including Corrective RAG, and considers how they compare and when to use them. ### Source excerpt Four retrieval techniques to improve RAG you need to know