发现基础模型：迈向开放式发现智能
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
浏览论文内容
中文总结 AI 辅助
本文提出发现基础模型（DFM）框架，将基础模型从问题求解扩展至参与新问题与知识的创造，并通过Zetema和GALILEO实例化，实现可学习、可执行、可评估的开放式发现智能。
中文摘要 AI 辅助
基础模型已从对现有知识的学习和推理，逐步发展到通过行动、工具使用和结果反馈进行学习。我们认为，下一个前沿是进一步的转变：从在人类指定问题内求解和行动，转向参与新问题、新表征、新解释和新知识的创造过程。我们将这种能力称为发现智能。我们将发现基础模型（DFMs）定义为用于开放式发现的通用模型系统。DFM 在可修订的研究状态上运行，并支持七种耦合能力，涵盖问题发现、问题表述、表征构建、假设形成、干预、基于证据的修订以及持续的发现改进。我们以 Zetema 实例化该框架，它结合了显式的研究状态动态、验证与实验门控、外部基础以及跨任务的发现技能演化。我们进一步以 GALILEO 夯实该框架，这是一个真实的治疗发现系统，其中干实验室推理、机器人和动手湿实验室实验、外部生物学证据以及迭代的假设和设计修订形成了一个闭环的物理发现回路。然后，我们制定了一种统一的能力形成和以过程为中心的评估方法，使得发现行为能够被训练、改进和衡量，而不仅仅是最终答案的性能。总之，这些组件将发现确立为基础模型系统的一种可学习、可执行和可评估的能力。我们将这一转变视为智能扩展的更广泛进展：从对现有知识的学习，到从行动结果中学习，最终参与到新知识被发现所依赖的结构的构建、测试和修订中。代码：此 https URL
英文摘要
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
