Search papers, labs, and topics across Lattice.
This paper introduces a scalable Enterprise Deep Research (EDR) architecture designed to improve the quality and consistency of enterprise research reports. The system decomposes research requests into coverage-driven objectives, localizes context using dependency-guided execution, and enforces evidence-based completion criteria. Experiments on a sales enablement task and the DeepResearch Bench benchmark demonstrate that this approach reduces premature stopping and improves research output quality compared to baselines.
Dependency-controlled context and explicit evidence sufficiency criteria are key to preventing premature stopping and improving the consistency of enterprise research outputs.
Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We propose a scalable Enterprise Deep Research (EDR) architecture to address these failures. Our system (i) decomposes requests into coverage-driven objectives via outline generation with reflection, (ii) localizes context with dependency-guided execution and explicit information sharing, and (iii) enforces evidence-based completion criteria so agents iteratively collect information until sufficiency conditions are met. We evaluate on an internal sales enablement task and the public DeepResearch Bench benchmark, where our proposed system design achieves the strongest overall performance compared with competitive deep-research baselines. The results show that dependency-controlled context and explicit evidence sufficiency criteria reduce premature stopping and improve the consistency and depth of enterprise research outputs.
