arXiv AI

A computable representation of the physical laboratory enables verifiable workflows

The paper introduces a computable representation of the physical laboratory that combines typed research objects, capability‑bound operations, and a compositional workflow algebra. This framework allows scientific workflows to be expressed as programs that track evolving laboratory states, including explicit dependencies, decisions, iteration, and concurrency. Implemented in a modular agentic robotic laboratory, the system binds formal operations to executable Function Skills, generates capability‑relative workflows for diverse scientific goals, and uses stateful simulation to verify operation preconditions and laboratory constraints before execution.

arXiv Machine Learning

Sep 25

LabFactory: Building and Evaluating Executable AI Labs

LabFactory is a framework that transforms a scientific brief into an executable AI lab, integrating models, knowledge resources, tools, and a controller behind a fixed interface. The builder packages the lab in a metered workspace, and a separate host evaluates the delivered artifact on held‑out inputs, ensuring the system itself is the evaluation target. Across 28 constructions in seven scientific domains, the delivered labs surpassed reference values on all 33 subtests, demonstrating that an AI agent can fully realize a scientific brief into a working, inspectable lab.

By Jinge Wu, Hongjian Zhou, Mingde Zeng, Jiayuan Zhu, Junde Wu, Jiazhen Pan, Lei Clifton, Andrew Liu, David A. Clifton

llms agents

arXiv AI

Jun 3

LAP: An Agent-to-Instrument Protocol for Autonomous Science

arXiv:2606. 03755v1 Announce Type: new Abstract: Autonomous science is moving from demonstration to infrastructure.

By Linwu Zhu, Liqiang Gao, Yan Chen, Dan Zhu, Jian Huang

llms agents robotics safety

arXiv AI

6d ago

SciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking of Scientific Embodied Agents

arXiv:2609. 30971v1 Announce Type: new Abstract: Embodied agents offer a promising route to automating scientific experimentation, yet their progress is constrained by the lack of reliable and systematic evaluation environments.

By Maokai Qin, Chuan Qin, Qi Zhang, Dianyu Liu, Zirui Liu, Hongting Niu, Yuanchun Zhou, Hengshu Zhu

agents robotics benchmarks

arXiv AI

Jul 7

Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator

arXiv:2509. 17255v2 Announce Type: replace-cross Abstract: We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source.

By Thorsten Hellert, Drew Bertwistle, Simon C. Leemann, Antonin Sulc, Marco Venturini

agents safety

arXiv AI

Jun 12

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

arXiv:2606. 13578v1 Announce Type: cross Abstract: Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach.

By Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu, Chenxi Li, Daqi Gao, Zeqin Su, Jintao Xing, Zirui Xue, Rui Li, Xiangyu Zhao, Shuofei Qiao, Minting Pan, Wangmeng Zuo, Lei Bai, Dongzhan Zhou, Ningyu Zhang, Huajun Chen

diffusion robotics multimodal benchmarks

arXiv AI

Jul 28

Stress-testing large language model agents in a robotic chemistry laboratory

arXiv:2607. 23045v1 Announce Type: new Abstract: AI is evaluated through knowledge, reasoning and plan generation, yet scientific agency requires reliable physical action and adaptation to evidence.

By Lulu Guo, Yingkai Sun, Xiaobo Li, Luyao Ge, Ziming Wang, Haitao Zheng, Jingyu Li, Huijuan Zhang, Bingxu Chen, Daobin Liu, Yuebo Liu, Jie Li, Xiaohui Li, Linjiang Chen, Yi Luo, Jun Jiang

llms agents robotics

arXiv AI

Aug 25

Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs

Physical Agentic AI proposes an architecture that links semantic planning with physical execution for robot crews. Each robot exposes a typed skill library, while a foundation model planner decomposes tasks into phases and assigns robot‑skill pairs. A Robot Orchestrator validates and authorizes one skill at a time, ensuring actions are grounded in robot capabilities, system state, and workflow constraints before actuation.

By Xinyuan Liu, Eren Sadikoglu, Riana Chatterjee, Ransalu Senanayake

llms agents robotics benchmarks

arXiv AI

Jun 12

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

arXiv:2606. 13662v1 Announce Type: new Abstract: LLM-based agents have shown increasing potential in automating scientific discovery.

By Amy Xin, Jiening Siow, Junjie Wang, Zijun Yao, Fanjin Zhang, Jian Song, Lei Hou, Juanzi Li

llms agents benchmarks

arXiv AI

Jun 30

BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation

arXiv:2605. 07306v2 Announce Type: replace-cross Abstract: Biological laboratory automation can reduce repetitive manual work and improve reproducibility, but reliable embodied execution in wet-lab environments remains challenging.

By Zhaohui Du, Zhe Wang, Hongmei Fei, Xiwen Cao, Ting Xiao, Qi Wang, Huanbo Jin, Jiaming Gu, Quan Lu, Zhe Liu

llms rag agents robotics multimodal benchmarks

arXiv AI

Jun 4

Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making

arXiv:2606. 04505v1 Announce Type: new Abstract: Scientific simulators are increasingly being integrated into LLM-driven systems for high-stakes simulation-driven decision-making.

By Yuhan Yang, Ruipu Li, Alexander Rodr\'iguez

llms agents

arXiv AI

2d ago

Can AI Scientists Coordinate at Runtime?

arXiv:2610.00980v1 Announce Type: cross Abstract: Multi-agent AI scientists have shown improving performance across a diverse range of tasks. Yet a common approach is design-time agentic orchestratio...

By Zijian Liu, Yangzhixin Luo, Junyu Lu, Yi Li, Yu Chen, David Xu, William F. Shen, Xinchi Qiu, Xisen Wang

agents

arXiv AI

Aug 3

Scaling Scientific Discovery Environments for Turn-Level Agentic RL

arXiv:2607. 28990v1 Announce Type: new Abstract: Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces a statistical claim.

By Yucheng Xu, Keyi Zhang, Yuyang Yu, Min Zhang, Shiyuan Meng, Pei Chu, Zhongying Tu

llms agents reinforcement-learning benchmarks

Related stories