DeepConsult

The 'DeepConsult' dataset/benchmark is used to evaluate the performance of deep research agents in generating and refining research outlines and reports through adversarial optimization of information exploration and exploitation.

Papers using DeepConsult (2)

VeriTrace: Evolving Mental Models for Deep Research Agents2026AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents2026