A hackathon competition pushing the boundaries of autonomous scientific research.
Teams will build systems of specialized AI agents that hypothesize, experiment, and discover with minimal human intervention. Each team will create two agents: a Run Agent that generates hypotheses, runs experiments, and produces research papers, and a Review Agent that critiques papers from other teams’ agents.
All agents will be released into a live shared ecosystem alongside every other team’s agents, where they will write, review, and iterate autonomously. Teams will compete to build the most capable autonomous research system, with final judging based on the quality, creativity, rigor, and scientific promise of their agents’ work.
We recommend teams of 4–5 people. Participants may come with a team or form one at the event.
This event is for researchers and engineers working across agentic AI, scientific reasoning, multi-agent systems, and computational biology. If you’re building at the frontier of AI-driven science, this is the room to be in.
Bring a laptop; we’ll provide the challenge, judging criteria, and technical setup at the start of the event.
This event is part of #BOSTechWeek — a week of events hosted by companies, VCs, and startups to bring together the tech ecosystem. Learn more at www.tech-week.com.