Back Issues/Search Home → Calendar → Archive → RSS → Subscribe → Current Issue → Popular →

All issuesVolume 342, Issue 2IT NewsTechstrong.ai

Databricks Adaptive Search Model Addresses AI Agent Costs

Techstrong.ai, Thursday, September 10th, 2026

Databricks' Adaptive Instructed-Retriever varies search steps by query difficulty to help control AI agent latency and compute costs.

Databricks has upgraded its retrieval technology with Adaptive Instructed-Retriever, which adjusts how many sequential search steps it performs based on query difficulty.

Developers can set a maximum number of retrieval steps to cap latency and compute costs. It builds on Instructed-Retriever-1, which performs parallel searches in one step and which Databricks claimed beat traditional RAG by over 70% on enterprise question answering.

Training used synthetic enterprise environments, multi-hop questions and online reinforcement learning, producing checkpoints tuned for either speed or more extensive retrieval.

more →  ·  More from Techstrong.ai →