Summary
QUEST is an open family of 2B to 35B deep research agents trained with fully synthetic rubric-tree tasks. The models target fact seeking, citation grounding, and report synthesis across objective and open-ended research benchmarks.
Key Features
Open family of deep research agents from 2B to 35B parameters.
Trained on fully synthetic rubric-tree tasks.
Targets fact seeking, report synthesis, and citation grounding.
Uses structured context management for research workflows.
Combines mid-training, supervised fine-tuning, and reinforcement learning.
Releases models, data, training code, and data-synthesis scripts.
Evaluated across eight deep-research and search benchmarks.
Provides paper, Hugging Face demo, model collection, and GitHub code links.
About QUEST
The training recipe combines rubric-tree-based task synthesis, structured context management, and a three-stage pipeline spanning mid-training, supervised fine-tuning, and reinforcement learning. The project emphasizes releasing models, data, data synthesis scripts, and training code.
QUEST is useful for researchers and developers building deep research agents that need to search, cite, and synthesize long-form reports. Its benchmark comparisons focus on broad research-agent capabilities rather than a single narrow search task.
Get more likes & reach the top of search results by adding this button on your site!
Subscribe to the AI Search Newsletter
Get top updates in AI to your inbox every weekend. It's free!