Nace AI Releases Drex for Search to Optimize Agent Document Retrieval
Nace AI has released Drex for Search, integrating decision models into document retrieval to provide AI agents with cited pages instead of fragmented chunks. By hierarchically narrowing the workspace from folders to specific table columns, it significantly improves accuracy and reduces search calls on benchmarks like BrowseComp-Plus. Developers can integrate this tool into coding agents such as Claude Code and Cursor via an MCP server, CLI, or SDKs.
Full Report
▲ Marktechpost AI · 2026-10-26 15
▲ Nace AI just released Drex for Search, which brings its Drex decision models to document search, so AI agents get cited pages instead of top-k chunks.
The key idea is that search is a series of decisions. Drex first classifies the question as a quick lookup or a deeper agent search. It then narrows the workspace from folder to file, section and page, down to table and column inside a sheet. Only the kept pages reach the LLM, and the answer cites the file and page.
The numbers, per Nace: 92.05% on BrowseComp-Plus with GPT-5, at 12.61 search calls per question, 16.6x fewer than the only entry ahead. 77.5% R@1 on VisDocAgentBench, 10 points above Claude Opus 5. 94.7% on MADQA with Gemini 3.5 Flash. On OfficeQA Pro, all 9 agent setups Nace tested needed fewer turns, with Claude Code on Opus 5.5 going from 18.5 to 9.1 turns.
Claude Code, Codex, Cursor and OpenCode can call it through the nace-mcp server or the CLI. There are also Python and TypeScript SDKs and a REST API......
Full analysis:
