Skip to content

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Sep 2026 · 5 citations · 59 references
Computer Science

TL;DR

This work forms a unified approach to capability formation and process-centered evaluation, enabling discovery behavior to be trained, improved, and measured beyond final-answer performance.

Abstract

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

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Euler: Towards Human-Centered Multi-Agent Mathematical Discovery

This work presents Euler, a human-centered mathematical research system built around a shared, structured representation of the research process that allows researchers to trace how results are developed and supplies agents with persistent, task-relevant knowledge for planning, collaboration, and verification across se...

Qiu-Yu Chen, Qi Wang, Liang Xu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction

Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation. We introduce OntoAct, a hypothesis-based neuro-symbolic framework built on ontological abstraction. OntoAct turns individual experiences into axioms over entity types, relations, and conditions, making th...

Donghyeok Lee, Bong Gyun Kang, Junyong Ahn et al. · 0 citations
#artificial intelligence Review Open access Sep 2026

ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI

The introduction of ScientistTwo, a fully autonomous multi-agent framework designed to realize problem-driven autonomous research, and its results show that ScientistTwo is not merely an assistive tool but an autonomous scientific pioneer capable of pushing the frontiers of human discovery.

Jaehyun Nam, Jinsung Yoon, Yan Pan et al. · 0 citations
Open access Aug 2025

Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants

ABSTRACT Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human oversight. Exponential growth of scientific literature and increasing domain sp...

Gabrielle Wehr, Reuben Rideaux, Amaya J. Fox et al. · 0 citations

State of Thought Enables Endogenous Reasoning

State of Thought is proposed, a new reasoning paradigm that enables endogenous reasoning in LLMs, with the model's internal reasoning state governing how reasoning unfolds, and provides a generalizable and efficient alternative to existing test-time reasoning paradigms.

Z. Gong, Yi-Kun Hou, Zi-Hao Zeng et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.