cs.AINov 7, 2026

Embodied Science Agents: Making Embodied Experimental Design Learnable

Authors: Yihang Che, Zhongwei Yu, Yang Li, Xingyu Lu, Hongxia Yu, Jun Wang

Organizations: University College London London, United Kingdom · AI Lab, The Yangtze River Delta China · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China · Shanghai Jiao Tong University Shanghai, China · 

Abstract

Recent advances in large models have accelerated AI for Science toward agentic science, where AI agents autonomously conduct scientific discovery. Realising this vision requires closing the loop between computational reasoning and physical experimentation, positioning self-driving laboratories (SDLs) as critical enablers. However, existing SDLs exhibit a fundamental paradox: foundation model integration has increased linguistic sophistication while severing physical grounding. By treating models as disembodied planners that output symbolic workflows for separate robotic systems, current architectures inherently block the development of embodied experimental intuition. We argue that overcoming this paradox requires embedding learnability along three interdependent axes: cognitive learnability (learning what to investigate), experimental learnability (learning where to search), and embodied learnability (learning how to act). Building on this view, we introduce the Embodied Science Agent (ESA), which unifies digital intelligence with physical embodiment through three synergistic components: a Digital Agent that provides cognitive and experimental learnability via memory-based reasoning and Bayesian optimisation, an Embodied Agent that provides embodied learnability via generalisable instrument control, and an Embodied Unified Interface for seamless coordination. We validated ESA in autonomous wastewater treatment experiments, navigating over 200 million possible conditions. Through 15 continuous rounds, ESA raised the final solution transmittance from 82% to 99.7%, corresponding to a 98.5% reduction in residual dye concentration and near-complete decolourisation, while its learned visuomotor policies generalised across varying instrument placements, a promising step toward next-generation SDLs for autonomous scientific discovery.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

    Mar 20, 2026Xiang Zhuang, Chenyi Zhou, Kehua Feng +10AI Agents for Scientific DiscoveryAutonomous Experimentation

  2. Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery

    May 6, 2026Zhenning Yang, Yuhan Chen, Patrick Tser Jern Kon +5AI for ScienceAI Agents for Scientific Discovery

  3. Compressing the Validation Bottleneck: An Agentic Self-Driving Lab for Scientific Discovery

    Jul 5, 2026Kyunghoon Hur, Chihun LeeAI for Scienceself-driving laboratories