Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
Paper defines Discovery Foundation Models with seven coupled capabilities for open-ended discovery, demonstrated via Zetema and GALILEO systems.
The paper formulates Discovery Foundation Models (DFMs) as general-purpose model systems for open-ended discovery, supporting seven coupled capabilities spanning problem discovery, formulation, representation construction, hypothesis formation, intervention, evidence-grounded revision, and continual improvement. It instantiates the framework with Zetema, which couples explicit research-state dynamics, verification and experimental gating, and cross-task Discovery Skill evolution. The framework is grounded with GALILEO, a real therapeutic-discovery system combining dry-lab reasoning with robotic wet-lab experimentation in a closed physical discovery loop; code is released on GitHub.
- DFMs aim to create new problems and knowledge, not just solve given tasks
- Zetema implements research-state dynamics and discovery skill evolution
- GALILEO couples dry-lab reasoning with robotic wet-lab experiments
From the original article
1 min read at huggingface.co
Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome feedback. We argue that the next frontier is a further transition: from solving and acting within problems specified by humans to participating in the process by which new problems, representations, explanations, and knowledge are created.
By Ling Yang, Zhenfei Yin, Yingcheng Wu · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.