Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
Proposes Discovery Foundation Models that participate in creating new problems and knowledge, instantiated in Zetema and the GALILEO therapeutic-discovery system.
The paper formulates Discovery Foundation Models (DFMs) as general-purpose systems for open-ended discovery, supporting seven coupled capabilities from problem discovery through evidence-grounded revision and continual improvement. It instantiates the framework with Zetema, combining explicit research-state dynamics, verification gating, external grounding, and cross-task Discovery Skill evolution. GALILEO, a real therapeutic-discovery system, closes the loop between Dry-Lab reasoning, robotic and hands-on Wet-Lab experimentation, and iterative hypothesis revision. The authors also define process-centered evaluation so discovery behavior can be trained and measured beyond final answers.
- Frames 'Discovery Intelligence' as next frontier beyond tool-use and reasoning
- DFMs support seven coupled capabilities including problem discovery and revision
- Zetema instantiates framework with verification gating and skill evolution
- GALILEO demonstrates closed physical discovery loop in therapeutic research
From the original article
1 min read at arxiv.orgFoundation 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 · arxiv.org
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.