Metraipolis › archive › dc_f4e8eae66230
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence — arXiv:2609.15973
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15973
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:16:25.708Z
- SHA-256 of the archived text
25a92c66c8cfc54d21f30d0245c5766a9db27d03f47ebd0e6049ce821721453c- Stable URL of this page
https://metraipolis.com/documento/dc_f4e8eae66230
How to cite
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence — arXiv:2609.15973 — arXiv (en), https://arxiv.org/abs/2609.15973 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4e8eae66230 (Metraipolis archive dc_f4e8eae66230, sha256 25a92c66c8cfc54d21f30d0245c5766a9db27d03f47ebd0e6049ce821721453c)
BibTeX
@misc{dcf4e8eae66230,
title = {Discovery Foundation Models: Toward Open-Ended Discovery Intelligence — arXiv:2609.15973},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15973},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4e8eae66230; sha256 25a92c66c8cfc54d21f30d0245c5766a9db27d03f47ebd0e6049ce821721453c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15973. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. We refer to this capability as Discovery Intelligence. We formulate Discovery Foundation Models (DFMs) as general-purpose model systems for open-ended discovery. A DFM operates over a revisable research state and supports seven coupled capabilities spanning problem discovery, formulation, representation construction, hypothesis formation, intervention, evidence-grounded revision, and continual discovery improvement. We instantiate this framework with Zetema, which couples explicit research-state dynamics, verification and experimental gating, external grounding, and cross-task Discovery Skill evolution. We further ground the framework with GALILEO, a real therapeutic-discovery system in which Dry-Lab reasoning, robotic and hands-on Wet-Lab experimentation, external biological evidence, and iterative hypothesis and design revision form a closed physical discovery loop. We then formulate a unified approach to capability formation and process-centered evaluation, enabling discovery behavior to be trained, improved, and measured beyond final-answer performance. Together, these components establish discovery as a learnable, executable, and evaluable capability of foundation-model systems. We view this shift as a broader progression in intelligence scaling: from learning over existing knowledge, to learning from action outcomes, and ultimately to participating in the construction, testing, and revision of the structures through which new knowledge is discovered. Code: this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.15973 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:51:09.971Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).