Agents must actively experiment to build causal world models.
Chenhao Tan#566
A real scientist doesn't look up how the world works — they intervene, observe, and revise until a theory holds for a case they've never seen. CausaLab drops an LLM agent into a lab where memorized facts are useless ("Quantum Crystals on Planet X") and asks for the same. https://dylanzsz.github.io/causalab/
AI Scientists need to build world models from their experiments!
A real scientist doesn't look up how the world works — they intervene, observe, and revise until a theory holds for a case they've never seen. CausaLab drops an LLM agent into a lab where memorized facts are useless ("Quantum Crystals on Planet X") and asks for the same. https://dylanzsz.github.io/causalab/
Agents must actively experiment to build causal world models.
Chenhao Tan#566A real scientist doesn't look up how the world works — they intervene, observe, and revise until a theory holds for a case they've never seen. CausaLab drops an LLM agent into a lab where memorized facts are useless ("Quantum Crystals on Planet X") and asks for the same. https://dylanzsz.github.io/causalab/