Mistral launches Agentic Search, a multi-step document retrieval layer

Agentic Search is Mistral's retrieval layer for AI systems. Instead of one-shot chunk retrieval, the model runs a multi-step loop over an existing search index, using five file-system-like tools (search, open, navigate, read, grep) to find, inspect, and verify information inside complex documents. It ships two ways: the open Mistral Search Toolkit for ingesting, embedding, and indexing data in the cloud or on-premises, plus ready-to-use libraries inside Studio and Vibe and a Search Starter App on GitHub. The design is model-agnostic and needs no fine-tuning, so retrieval quality scales with model capability rather than being capped by the chunking strategy. Mistral reports large gains on default, untuned settings: FinanceBench (SEC filings) correctness from 26.7% to 86%, OfficeQA Pro (Treasury Bulletins) from 6.3% to 51.9%, p90 latency down up to 39.6%, and token use down up to one-third, tested with both Mistral Medium 3.5 and Z.ai GLM-5.2.

One-shot RAG fails structurally on questions that require navigating long reports, comparing sources, or reading tables and footnotes; Agentic Search gives the model iterative document operations instead of better chunking. The index stays inside your own perimeter, and the open Toolkit route makes it viable for sensitive enterprise data. Because it is model-agnostic, you can benchmark it against your own stack. Caveats: the numbers are vendor-reported, measured on document-heavy domains, and pricing was not stated, so independent reproduction is still pending.