AI Briefing#rag
The latest AI and developer news about #rag, with the original source and a short summary.
The latest AI and developer news about #rag, with the original source and a short summary.
After calibrating an LLM with a small amount of human labels, it automatically generates relevance labels at scale.
InsightLens uses RAG and LLMs to turn natural language into executable SQL.
Furiosa SDK 2026.1 strengthens batching, caching, and Kubernetes support.
Noting that the optimal chunk size differs for each query, combining chunks of multiple sizes improved RAG retrieval performance by up to 37%.
Dropbox Dash reduces tokens and latency through index, knowledge graph, and MCP optimization.
TRUSTBANK has launched 'Choice AI,' which uses OpenAI models and a multi-agent architecture to personalize and recommend Furusato Nozei return gifts.
Word Shape Encoding significantly boosts Hebrew and Arabic PDF parsing quality.
AI21 has proposed Boring Agents, which prioritize predictability and auditability.
In 2025, the deciding factor in enterprise AI was system design, not model performance.
Mongolia Customs automated HS Code classification with an LLM/RAG-based NPU chatbot.
SK Planet is building AI competitiveness through service and data optimization rather than developing its own LLM.
This explains technical methodologies for enabling LLMs to effectively understand PDF documents with complex structures.
6G is evolving beyond a speed race into an autonomous network fabric with AI built in.
Dash improved agent accuracy by reducing the number of tools and keeping only relevant context.
PlaceAI automated backoffice knowledge search using RAG+MCP and hybrid search.
SK Planet unveiled the results of its 2025 AI and technology education programs for developer growth.
LY Corporation unveiled its technology innovation strategy through 'Tech-Verse 2025', centered on AI agent adoption and integration of its proprietary cloud.
Hugging Face has unveiled RTEB, a new retrieval embedding benchmark designed to precisely measure a model's generalization ability.
OpenAI built a RAG-based contract data agent to solve the bottleneck in contract review work and maximize operational efficiency.
AI reduced deployment note generation time by 80% and automated risk analysis based on past incident cases.
Kakao's level-based customized AI education resulted in over 60% of all tech roles participating in the AI Basic course and over 60% of all developers acquiring generative AI application capabilities.
Function Calling, RAG, and LangGraph were used to improve the accuracy and operability of a consultation-style chatbot.
Google has released EmbeddingGemma, a 308M-scale multilingual embedding model optimized for on-device environments.