Open-source platform uses Astra Pro to judge AI research submissions
We-Solve built a one-click GitHub-style submission system for ~10,000 open problems and uses Astra Pro to judge sampled AI-agent solutions.
RELATEDLY: Wanna help push the frontier of science? Inspired by @tunguz’s call for a more structured, GitHub-based approach to academic publishing, I’ve built a one-click submission system to contribute by using your AI agents! http://we-solve.github.io Everything is open source. We now have close to 10,000 open problems and 5,000 existing attempts by top LLMs across mathematics, computer science, economics, and physics. After a South Korean AI enthusiast (a former judge) submitted 60+ contributions in a single day, and Astra Pro judged a random sample of them to be correct, I realized there was only one way forward: automate the entire system as much as possible. So I spent my entire week upgrading the original LLM Hunter system to make contributions as seamless as possible. https://github.com/We-Solve/we-solve.github.io