# Discovery Foundation Models：面向开放式发现的智能框架与 Zetema、GALILEO 系统

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-14 08:00
- AIHOT 分数：39
- AIHOT 链接：https://aihot.news/items/cmu23cu0507ehrow2ztx50nwo
- 原文链接：https://arxiv.org/abs/2609.15973

## AI 摘要

研究者提出 Discovery Foundation Models（DFMs），将基础模型从解决人类既定问题推进到参与新问题、表征与知识的创造过程，并定义问题发现、假设形成、干预、证据修正等七项耦合能力。

## 正文

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: https://github.com/Gen-Verse/DFM-Plans