RAG

RAG, or retrieval-augmented generation, is a pattern that grounds a language model’s answer in documents, code, or data fetched at query time rather than relying only on what the model memorized in training. A retriever finds the most relevant passages, and the model generates its answer conditioned on them.

For builders it is the cheapest way to make an LLM answer over private, fresh, or domain-specific knowledge without retraining, and citations make the answers auditable. The quality ceiling is set by retrieval: if the right passage is never fetched, no amount of prompting recovers it.

The common failure is treating RAG as a single trick instead of a pipeline — Chunking, Embeddings, Hybrid Search, Reranking, and RAG Evaluation each move the needle, and a weak link surfaces as a confident but ungrounded answer.

Related: Embeddings Vector Database Hybrid Search Reranking Chunking Context Engineering RAG Evaluation

This is the RAG concept page (definitions and fundamentals). For dated developments, see the RAG Topic hub.

Recent Updates

• 2026-07-21: An agent caught its own false success report using memory (Все статьи подряд / Искусственный интеллект / Хабр) · habr.com — MiniLM
• 2026-07-22: RF-Agent builds an RF reasoning dataset and benchmark from textbooks (cs.CL updates on arXiv.org) · arxiv.org
• 2026-07-22: ProbSPARQL adds uncertainty-aware querying to RDF and SPARQL (cs.AI updates on arXiv.org) · arxiv.org
• 2026-07-22: FiT studies how fine-tuning affects small LLMs for cybersecurity QA (cs.CL updates on arXiv.org) · arxiv.org
• 2026-07-22: Fusion Embedding proposes one shared embedding space for text, image, video, and audio (cs.CL updates on arXiv.org) · arxiv.org — arXiv Abdul Basit Tonmoy fusion-embedding-1 fusion-embedding-2
• 2026-07-22: Search-on-Graph-R1 trains an 8B model to search knowledge graphs with SFT and RL (cs.CL updates on arXiv.org) · arxiv.org — Freebase Search-on-Graph-R1
• 2026-07-22: SimpleOne argues for a unified GenAI platform for enterprise automation (Все статьи подряд / Искусственный интеллект / Хабр) · habr.com — SimpleOne Active Directory · Habr Ilya Radchenko
• 2026-07-22: Our AI agent failed at production tasks, but became useful for analyst research (Все статьи подряд / Искусственный интеллект / Хабр) · habr.com — Confluence
• 2026-07-22: OpenClaw on NixOS as a declarative AI assistant with long-term memory (Все статьи подряд / Искусственный интеллект / Хабр) · habr.com — OpenClaw · NixOS · Telegram QMD agenix Garnix Home Manager · GLM-4.7-Flash
• 2026-07-22: Claude can answer questions over Anthropic’s Economic Index dataset (Anthropic) · x.com — Anthropic
• 2026-07-23: Screenpipe adds local screen-and-audio capture as searchable memory for agents (Hacker News) · news.ycombinator.com — Hacker News Screenpipe · YC Tella · YouTube · Obsidian · OpenAI · Anthropic Louis Karpathy Garry gpt2 GPT3 · Parakeet · Whisper
• 2026-07-24: Retrieval-augmented multi-agent LLM workflow for detecting cutaneous immune-related adverse events (cs.CL updates on arXiv.org) · arxiv.org
• 2026-07-24: TopoGuard uses graph topology to detect split-knowledge attacks in RAG (cs.CL updates on arXiv.org) · arxiv.org — arXiv LlamaGuard LlamaGuard-2-8B
• 2026-07-24: THOR proposes a hierarchical oscillatory reasoning framework for multi-hop QA (cs.CL updates on arXiv.org) · arxiv.org
• 2026-07-24: Chronofy adds temporal decay to RAG retrieval and reasoning (cs.LG updates on arXiv.org) · arxiv.org
• 2026-07-24: ExecuGraph evaluates a multi-agent, execution-checked backend code synthesis workflow (cs.AI updates on arXiv.org) · arxiv.org — arXiv · Ollama DeepSeekCoder V2 Lite
• 2026-07-24: Optimizing Hypergraph-Based RAG with better extraction and retrieval (cs.AI updates on arXiv.org) · arxiv.org
• 2026-07-24: Gold-Anchored Evaluation and Guard for Citation Faithfulness in Agentic Scientific Synthesis (cs.AI updates on arXiv.org) · arxiv.org — OpenScholar PaperQA2
• 2026-07-24: CORE: Contrastive Reflection for faster reasoning improvement (alphaXiv) — Linas Nasvytis Simon Jerome Han Ben Prystawski Satchel Grant Noah D. Goodman Judith E. Fan GRPO GEPA MemRL
• 2026-07-27: Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA (cs.LG updates on arXiv.org) · arxiv.org
• 2026-07-27: Trajectory-Aware Retrieval Agents for Temporal Decision-Making (cs.AI updates on arXiv.org) · arxiv.org
• 2026-07-27: Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination (cs.CL updates on arXiv.org) · arxiv.org — Gemma-4-31B-IT · Gemini
• 2026-07-28: A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever (cs.CL updates on arXiv.org) · corbenic-galahad-bench.hf.space — Hugging Face
• 2026-07-28: Small language models need fine-tuning to effectively use provided legal context (cs.CL updates on arXiv.org) · huggingface.co — Qwen3.5
• 2026-07-28: Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering (cs.CL updates on arXiv.org) · arxiv.org

FAQ

What is RAG?

RAG, or retrieval-augmented generation, grounds LLM answers in retrieved documents, code, or data before generation. GROUNDING tracks RAG architecture, retrieval quality, evaluation, grounding failures, and production patterns.

Which concepts are related to RAG?

Related concepts tracked by the radar include Embeddings, Vector Database, Hybrid Search, Reranking, Chunking.

What does this RAG page track?

Dated updates, papers, and mentions of RAG collected by the GROUNDING radar, most recently on 2026-07-28.