Nace AI Releases Drex for Search to Optimize Agent Document Retrieval

1 reports archived1 independent sourcesupdated 10/26/2026, 23:41:23

Synthesis & Latest Updates

1 Sources Cross-Validated

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.

LATEST/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.

Hourly heat curve

4 fully observed hours

Now

11.6

Peak

12.510-28

24h change

–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first

Marktechpost (@Marktechpost)T2Oct 26, 23:41·78 pts
Nace AI Releases Drex for Search to Optimize Agent Document Retrieval
- Adopts a 'search-as-decisions' paradigm, classifying queries first and then hierarchically narrowing scope from files to table columns, providing only high-relevance full pages to the LLM.
- Achieves 92.05% accuracy on BrowseComp-Plus while reducing average search calls to 12.61 per question (16.6x fewer than the leading entry).
- Seamlessly integrates with agent environments like Claude Code, Codex, and Cursor via nace-mcp server, CLI, Python/TypeScript SDKs, and REST API.
View Related Reports & Analysis Original Source