Agentic relevance tuning: Letting LLM agents do the search engineering work

Introduced at OpenSearchCon Europe 2026, Agentic Relevance Tuning (ART) is a new framework that uses specialized LLM agents to automate the entire search relevance lifecycle in OpenSearch. By continuously monitoring user behavior and automatically validating ranking improvements through offline evaluations, ART transforms the complex, manual task of tuning search results into an automated infrastructure capability.