The original RAG paper (Lewis et al., 2020), explained
Retrieval-Augmented Generation was named in a 2020 paper by Patrick Lewis and colleagues. What it proposed, how the original architecture worked, and how today's RAG differs from it.
RAG Research
A closer look at where Retrieval-Augmented Generation is heading. Each piece digs into a strand of recent research, cites the key papers, and draws out what it means for the systems you are building today.
RAG evaluation gets specific: the 2026 wave of domain benchmarks
General leaderboards like BEIR and MTEB told you which retriever was good in the abstract. A wave of 2024 to 2026 benchmarks asks a harder question: good at what, for whom? A tour of domain, task, and contamination-resistant RAG evaluation, and how to use it.
Read RAG evaluation gets specific: the 2026 wave of domain benchmarks
Agentic RAG: teaching models to run their own searches
A new line of work trains the model itself to decide when and what to retrieve, interleaving reasoning with live search. A look at RL-trained search agents like Search-R1, and what they change for RAG.
Long context or RAG? What the research actually says
As context windows stretch into the millions of tokens, does retrieval still earn its place? A look at the evidence on long-context models versus RAG, and why the answer is usually both.
Visual document retrieval: RAG over pages, not text
Most RAG pipelines OCR a PDF, then chunk the text, and lose the tables, charts and layout on the way. A newer approach embeds the page image itself. A look at ColPali, ViDoRe and OCR-free retrieval.
Reasoning-intensive retrieval: where dense search breaks
Embedding search excels when the answer looks like the question. When relevance needs reasoning, not surface similarity, even top retrievers fall apart. A look at the BRIGHT benchmark and what it means for RAG.
Read Reasoning-intensive retrieval: where dense search breaks
Reranking and two-stage retrieval: precision after recall
A fast first-stage retriever casts a wide net; a slower reranker sorts what it catches. How cross-encoders and late-interaction models like ColBERT sharpen RAG retrieval, and when the extra stage pays off.
Read Reranking and two-stage retrieval: precision after recall
GraphRAG: when a knowledge graph beats plain vector search
Vector search retrieves passages that look similar to the query. For multi-hop and whole-corpus questions, structure helps. A look at graph-based retrieval, from Microsoft GraphRAG to knowledge-graph grounding.
Read GraphRAG: when a knowledge graph beats plain vector search
Measuring RAG faithfulness: is the answer actually supported?
A RAG system can retrieve the right passage and still write an answer the passage does not support. Measuring that gap, faithfulness, is its own hard problem. A look at RAGTruth, LLM-as-judge, and what to trust.
Read Measuring RAG faithfulness: is the answer actually supported?
Long-term memory for agents: beyond the context window
Retrieval fetches from a fixed corpus; memory decides what an agent should carry forward from its own past. A look at write, consolidate and forget systems like MemGPT and Mem0, and their limits.
Self-correcting RAG: retrieval that knows when it is wrong
Naive RAG retrieves and hopes. A newer line of work lets the model decide when to retrieve, judge whether the passages are any good, and correct course. A look at Self-RAG, Corrective RAG and where this is heading.
Read Self-correcting RAG: retrieval that knows when it is wrong