Building Deep Research: How we Achieved State of the Art

Summary

Building production AI research agents presents challenges around context window pollution, escalating token costs, and architectural brittleness across model updates. To resolve these issues, Tavily rebuilt its deep research system around simplified orchestration, compact tooling, and active context curation. The agent mimics human research workflows by distilling tool outputs into concise reflections for ongoing reasoning, withholding raw retrieved web data until the final deliverable stage. Compared to traditional ReAct propagation architectures where token consumption scales quadratically, this reflection-based approach achieves linear token growth. As a result, the system reduced token consumption by 66% compared to Open Deep Research while reaching state-of-the-art performance on DeepResearch Bench.

Takeaways

1. 1

   Distilling tool outputs into reflections rather than propagating raw web tokens changes tool-calling context growth from quadratic to linear, reducing token consumption by 66% relative to Open Deep Research.

2. 2

   Global state persistence and source deduplication keep agent context fresh, signal when information scope is narrowing to trigger broader exploration, and enable accurate source attribution.

3. 3

   Providing a smaller, essential toolset reduces failure modes compared to large toolsets, helping models reliably choose tools and avoid iterative breakdowns.