Quit: A Human-in-the-Loop Platform for AI Research Automation (github.com)

QUIT has been launched as a revolutionary human-in-the-loop platform designed to automate AI research processes. The platform offers a transparent, artifact-driven workflow that enables researchers to maintain control throughout their projects. By employing four specialized agents—Planner, Research, Builder, and Reviewer—QUIT allows users to query literature, extract insights, implement experiments, and draft papers while keeping the entire process traceable and reproducible. The system's architecture facilitates both guided and end-to-end processing, with costs estimated at roughly $1.50 per manuscript. This innovation is significant for the AI/ML community as it addresses common bottlenecks in research pipeline management, enhancing reproducibility and efficiency. Researchers can seamlessly intervene at any stage, ensuring high-quality outputs while benefiting from the automated generation of experimental code and scholarly articles. With its open-source availability and support for multiple LLM providers, QUIT presents an accessible tool for both novice and experienced researchers looking to expedite their workflows and explore new areas of inquiry.