Research
Towards rigorous, reliable, and capable AI scientists
AI-generated research can read as convincing while being wrong or impossible to reproduce. We build the infrastructure that makes an AI scientist trustworthy in what it claims, auditable in how it got there, and guided by real taste for what is worth discovering.
The Last Human-Written Paper: Agent-Native Research Artifacts
What if a paper were something an AI could run and verify, not just read?
Sci-Reasoning: A Dataset Decoding AI Innovation Patterns
How do the best researchers actually arrive at their breakthroughs, and could an AI learn to do the same?
EXP-Bench: Can AI Conduct AI Research Experiments?
Today's agents can design and code an experiment, so why can almost none of them finish one?
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
How do you make an AI scientist's experiments rigorous enough to trust the results?
AI-scientist work only · full publication list on amberljc.github.io.