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

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

Research faces bottleneck due to flawed human evaluation methods

AI agents map resonators across biology, engineering, and music, discovering a design gap and generating a novel bio-inspired structure.

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

New research paper identifies multi-tool coordination as the primary failure point for AI agents, shifting focus from single-step execution to multi-step orchestration.

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

New AI agent designed to autonomously execute 'buy the dip' investment strategies reported by WSJ