Industry projections forecast agents handling 50% of online transactions by 2027

Gartner projects 40% of enterprise applications will feature task-specific AI agents by 2026

New RAG paradigm with iterative retrieval at multiple reasoning steps achieves 15-20% accuracy gain on HotpotQA

AI agent ordered surplus candles due to lack of guardrails in inventory management

Positioned as go-to technique for dynamic, fact-heavy applications with frequently changing information

Research exposed a critical vulnerability where just 5 poisoned documents can corrupt RAG systems.

Clarification article published explaining distinction between RAG and fine-tuning for LLM applications

Publication of a framework moving RAG systems from proof-of-concept to production, outlining anti-patterns and a five-pillar architecture.

Ethan Mollick declared the end of the 'RAG era' as dominant paradigm for AI agents

Researchers propose test-time modifications to agentic RAG systems with contextualization and de-duplication modules