Research

Paper

AI LLM March 20, 2026

Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

Authors

Xiang Zhuang, Chenyi Zhou, Kehua Feng, Zhihui Zhu, Yunfan Gao, Yijie Zhong, Yichi Zhang, Junjie Huang, Keyan Ding, Lei Bai, Haofen Wang, Qiang Zhang, Huajun Chen

Abstract

Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most current computational approaches are misaligned with this reality, framing discovery as isolated, task-specific predictions rather than continuous interaction with the physical world. Here, we argue for embodied science, a paradigm that reframes scientific discovery as a closed loop tightly coupling agentic reasoning with physical execution. We propose a unified Perception-Language-Action-Discovery (PLAD) framework, wherein embodied agents perceive experimental environments, reason over scientific knowledge, execute physical interventions, and internalize outcomes to drive subsequent exploration. By grounding computational reasoning in robust physical feedback, this approach bridges the gap between digital prediction and empirical validation, offering a roadmap for autonomous discovery systems in the life and chemical sciences.

Metadata

arXiv ID: 2603.19782
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-20
Fetched: 2026-03-23 16:54

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.19782v1</id>\n    <title>Embodied Science: Closing the Discovery Loop with Agentic Embodied AI</title>\n    <updated>2026-03-20T09:20:12Z</updated>\n    <link href='https://arxiv.org/abs/2603.19782v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.19782v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most current computational approaches are misaligned with this reality, framing discovery as isolated, task-specific predictions rather than continuous interaction with the physical world. Here, we argue for embodied science, a paradigm that reframes scientific discovery as a closed loop tightly coupling agentic reasoning with physical execution. We propose a unified Perception-Language-Action-Discovery (PLAD) framework, wherein embodied agents perceive experimental environments, reason over scientific knowledge, execute physical interventions, and internalize outcomes to drive subsequent exploration. By grounding computational reasoning in robust physical feedback, this approach bridges the gap between digital prediction and empirical validation, offering a roadmap for autonomous discovery systems in the life and chemical sciences.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-20T09:20:12Z</published>\n    <arxiv:comment>Work in progress</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Xiang Zhuang</name>\n    </author>\n    <author>\n      <name>Chenyi Zhou</name>\n    </author>\n    <author>\n      <name>Kehua Feng</name>\n    </author>\n    <author>\n      <name>Zhihui Zhu</name>\n    </author>\n    <author>\n      <name>Yunfan Gao</name>\n    </author>\n    <author>\n      <name>Yijie Zhong</name>\n    </author>\n    <author>\n      <name>Yichi Zhang</name>\n    </author>\n    <author>\n      <name>Junjie Huang</name>\n    </author>\n    <author>\n      <name>Keyan Ding</name>\n    </author>\n    <author>\n      <name>Lei Bai</name>\n    </author>\n    <author>\n      <name>Haofen Wang</name>\n    </author>\n    <author>\n      <name>Qiang Zhang</name>\n    </author>\n    <author>\n      <name>Huajun Chen</name>\n    </author>\n  </entry>"
}