A developer built three question-answering pipelines — RAG, GraphRAG, and Agentic GraphRAG — on TigerGraph Savanna to test when agentic loops actually beat simpler retrieval, using ~2,900 Wikipedia Ol…
Graph-based contextual retrieval, which uses GraphRAG to traverse a context graph rather than relying on vector similarity alone, improves AI agent accuracy by following explicit relationships between…
DX's newly published CAFE(S) framework evaluates the quality of context given to AI agents across five dimensions — Clarity, Actionability, Fidelity, Efficiency, and Security — and is positioned as co…
TRACE, a tree-relational enhancement framework for oncology large language models, improved label-free evaluation and supervised fine-tuning across ten oncology classification tasks and the MedQuAD Ca…
Fine-tuning, including techniques such as LoRA and QLoRA, offers a way to customize language models when prompting and retrieval-augmented generation (RAG) leave recurring gaps, according to an articl…
Roughly 60% of production LLM deployments now use retrieval-augmented generation (RAG) and fine-tuning together, according to a Scalacode analysis, because the two techniques solve different problems …
A new method called Document Retrieval-Aware Chunking (D-RAC) aims to make ingestion of enterprise documents into Retrieval-Augmented Generation (RAG) systems universal by normalizing PDFs and convert…
Aster Market, an early marketplace focused on bounded digital services, is arguing that AI-agent marketplaces should prioritize verifiable delivery over listing volume. The project proposes that listi…
Agentic RAG differs from standard retrieval-augmented generation because the model decides how and when to retrieve context as a tool rather than following a fixed developer-defined pipeline, accordin…
The GitHub Podcast's latest episode argues that four common AI hot takes — that developers need not read AI-generated code, that companies will not hire developers who avoid AI, that Skills killed the…
A new arXiv paper (2609.16564v1) proposes a pre-generation triage layer for retrieval-augmented generation (RAG) pipelines that treats a source's material relationship to the query as query dependent,…
A new installment in the LLM Evaluation series argues that AI applications such as Retrieval-Augmented Generation (RAG) chatbots require multiple parallel evaluation pipelines rather than a single eva…
A Medium post in the "AI in Plain English" series argues that BM25 keyword ranking remains essential to retrieval-augmented generation (RAG) systems even as embeddings draw widespread attention. The a…
A technical textbook titled "Foundation Model Engineering: From Theory to Production" is being released for AI engineers and research-oriented readers, covering architectures, training pipelines, infe…
Database administrators should treat AI as a process-following diagnostic assistant rather than a replacement, according to an InfoWorld opinion piece marking PostgreSQL's 30th anniversary. The author…
Daniel Miessler outlined a two-layer personal knowledge management (PKM) architecture that he argues makes a truly personal AI possible, with raw source documents kept untouched in a lower layer and a…
AllSpark released Iris-mini and Iris-pro, two open-weight search agents built on Qwen architectures and tuned for search and tool-use, which the team says lead their respective size classes in search-…
A developer argues that AI learners should prioritize building real projects over collecting certificates, outlining a progression from data projects and deployed machine learning applications to sema…
Air Canada lost a legal case in late 2022 when its customer service chatbot provided incorrect bereavement fare information, leading to a passenger's successful lawsuit. The failure stemmed from a RAG…
ByteByteGo's newsletter EP224 explains the differences between MCP, RAG, and AI agents, defining MCP as an open standard protocol for connecting AI models to external tools, RAG as a method for fetchi…