Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.04375 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918505186590720 |
|---|---|
| author | Yang, Zhenning Chen, Yuhan Kon, Patrick Tser Jern Miao, Tongyuan Lin, Hongyi Viswanathan, Venkat Koutra, Danai Chen, Ang |
| author_facet | Yang, Zhenning Chen, Yuhan Kon, Patrick Tser Jern Miao, Tongyuan Lin, Hongyi Viswanathan, Venkat Koutra, Danai Chen, Ang |
| contents | To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent's ability to control and explore in real-world labs is essential because the physical lab remains foundational to scientific discovery. While some tasks can be performed on a computer (e.g., data analysis, running simulated experiments), Eureka moments could occur at any time while operating lab instruments (e.g., when a scientist notices unexpected clues, intuition may prompt a real-time course change). Although autonomous labs are on the rise, which expose programmable APIs to control scientific instruments via software, bridging the gap between increasingly powerful AI agents and automated lab equipment requires innovation that draws insights from computer systems.
We propose a new paradigm called ``Experiment-as-Code (EaC) Labs,'' where a core concept is to encode experiments as declarative configurations that can be compiled down to device-level APIs. AI agents come up with hypotheses and experiments, written as an ensemble of declarative configurations. The systems layer performs program analysis, safety checks, resource assignment, and job orchestration. Finally, programmatic experimentation occurs via actuating the device APIs. This is a general stack that is science-, lab-, and instrument-independent, representing a novel synthesis across the physical, systems, and intelligence layers to unleash the next breakthrough in AI for Science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04375 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery Yang, Zhenning Chen, Yuhan Kon, Patrick Tser Jern Miao, Tongyuan Lin, Hongyi Viswanathan, Venkat Koutra, Danai Chen, Ang Systems and Control Artificial Intelligence To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent's ability to control and explore in real-world labs is essential because the physical lab remains foundational to scientific discovery. While some tasks can be performed on a computer (e.g., data analysis, running simulated experiments), Eureka moments could occur at any time while operating lab instruments (e.g., when a scientist notices unexpected clues, intuition may prompt a real-time course change). Although autonomous labs are on the rise, which expose programmable APIs to control scientific instruments via software, bridging the gap between increasingly powerful AI agents and automated lab equipment requires innovation that draws insights from computer systems. We propose a new paradigm called ``Experiment-as-Code (EaC) Labs,'' where a core concept is to encode experiments as declarative configurations that can be compiled down to device-level APIs. AI agents come up with hypotheses and experiments, written as an ensemble of declarative configurations. The systems layer performs program analysis, safety checks, resource assignment, and job orchestration. Finally, programmatic experimentation occurs via actuating the device APIs. This is a general stack that is science-, lab-, and instrument-independent, representing a novel synthesis across the physical, systems, and intelligence layers to unleash the next breakthrough in AI for Science. |
| title | Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery |
| topic | Systems and Control Artificial Intelligence |
| url | https://arxiv.org/abs/2605.04375 |