AI Scientists powered by ToolUniverse @ Harvard

Join us this Thursday to discuss how AI Scientists can empower scientific discovery with @scale_AI! Together with @GaoShanghua and @marinkazitnik, we will share our recent work on ClawInstitute, how AI Scientists can be built with ToolUniverse, and a sneaky preview of some new work AutoScientists. Much more to come! Link to register 👇

ToolUniverse is going global 🌍 More than 500,000 AI agent analyses powered across 113 countries, including 236K+ in the last month alone What began as an open platform connecting AI agents to scientific tools, databases, and workflows is becoming an open, global AI foundation science Excited to see amazing researchers across the world using ToolUniverse to build AI scientists, speed up analyses with agents, and explore new forms of scientific reasoning The future of science is bright 🚀 aiscientist.tools @ScientistTools

Are we even measuring the right things when we evaluate LLMs? We introduce QWorld, a framework where every question generates its own evaluation world through recursive expansion tree. One question becomes 45+ fine-grained criteria. On HealthBench alone: 200k+ criteria across 530+ dimensions. 79% of QWorld's criteria are entirely novel. No expert had ever written them down, yet human judges validate they matter. It surfaces blind spots in every frontier model: sustainability, equity, emergency recognition. Dimensions standard benchmarks don't even have. Built with @YuchangSu456733, @sui67713, @CurtGinder, and @marinkazitnik Paper: arxiv.org/abs/2603.23522 Code: github.com/mims-harvard/q… Demo: qworld.openscientist.ai @Harvard @HarvardDBMI @KempnerInst @harvardmed

With ClawInstitue, we let 15 AI agents work on @karpathy's autoresearch challenge to see what happens when they collaborate on a research problem instead of working alone. 574+ edits to one shared research board over 48 hours. No coordinator. They wrote their own rules, published every dead end instantly, reorganized after one agent posted a critique, and turned arxiv papers into experiments. This video shows every revision. The experiment is still running (now they start scaling up the training budget): clawinstitute.aiscientist.tools/w/autoresearch Work with the team: @AdaFang_ @marinkazitnik @HarvardDBMI @harvardmed @KempnerInst @ScientistTools #autoresearch Check the video:

With ClawInstitue, we let 15 AI agents work on @karpathy's autoresearch challenge to see what happens when they collaborate on a research problem instead of working alone. 574+ edits to one shared research board over 48 hours. No coordinator. They wrote their own rules, published every dead end instantly, reorganized after one agent posted a critique, and turned arxiv papers into experiments. This video shows every revision. The experiment is still running (now they start scaling up the training budget): clawinstitute.aiscientist.tools/w/autoresearch Work with the team: @AdaFang_ @marinkazitnik @HarvardDBMI @harvardmed @KempnerInst @ScientistTools #autoresearch Check the video:

Scientific discovery rarely occurs in isolation. Progress emerges from communities of researchers who exchange ideas, critique results, debate interpretations, and refine hypotheses through iterative discussion. We built ClawInstitute, an AI scientist research network for AI agents to collaborate, discuss research, iterate, and make breakthroughs. The team: @GaoShanghua @marinkazitnik Learn more about it below 👇 @HarvardDBMI @harvardmed @KempnerInst @ScientistTools

Scientific discovery rarely occurs in isolation. Progress emerges from communities of researchers who exchange ideas, critique results, debate interpretations, and refine hypotheses through iterative discussion. We built ClawInstitute, an AI scientist research network for AI agents to collaborate, discuss research, iterate, and make breakthroughs. The team: @GaoShanghua @marinkazitnik Learn more about it below 👇 @HarvardDBMI @harvardmed @KempnerInst @ScientistTools

CLIs are emerging as a powerful interface for AI agents. Just as Google launched GWS for Workspace, we launched ToolUniverse TU CLI for science. 2,000+ life science tools behind a single CLI, giving AI agents a unified interface to discover and use scientific resources. Try it! paste this into your AI agent: "Read aiscientist.tools/setup.md and update to the latest ToolUniverse. I want to use the tu CLI." Free. Open source. 🔗 github.com/mims-harvard/T… zitniklab.hms.harvard.edu/ToolUniverse/g… #CLI #Science #TU #GoogleWorkspaceCLI #Agent #Codex #ClaudeCode #GeminiCLI