A multi-agent-driven robotic AI chemist enabling autonomous chemical research on demand DOI Creative Commons
Tao Song, Man Luo, Linjiang Chen

и другие.

Опубликована: Июль 30, 2024

The successful integration of large language models (LLMs) into laboratory workflows has demonstrated robust capabilities in natural processing, autonomous task execution, and collaborative problem-solving. This offers an exciting opportunity to realize the dream chemical research on demand. Here, we report a robotic AI chemist powered by hierarchical multi-agent system, ChemAgents, based on-board Llama-3-70B LLM, capable executing complex, multi-step experiments with minimal human intervention. It operates through Task Manager agent that interacts researchers coordinates four role-specific agents—Literature Reader, Experiment Designer, Computation Performer, Robot Operator—each leveraging one foundational resources: comprehensive Literature Database, extensive Protocol Library, versatile Model state-of-the-art Automated Lab. We demonstrate its versatility efficacy six experimental tasks varying complexity, ranging from straightforward synthesis characterization more complex exploration screening parameters, culminating discovery optimization functional materials. Our multi-agent-driven showcases potential on-demand drive unprecedented efficiencies, accelerate discovery, democratize access advanced across academic disciplines industries.

Язык: Английский

From screens to scenes: A survey of embodied AI in healthcare DOI
Yihao Liu, Xu Cao, Tingting Chen

и другие.

Information Fusion, Год журнала: 2025, Номер unknown, С. 103033 - 103033

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

2
Research and Application of a Multi-Agent-Based Intelligent Mine Gas State Decision-Making System DOI Creative Commons
Yi Sun, Xinke Liu

Applied Sciences, Год журнала: 2025, Номер 15(2), С. 968 - 968

Опубликована: Янв. 20, 2025

To address the issues of low efficiency in manual processing and lack accuracy judgment within traditional mine gas safety inspections, this paper designs implements Intelligent Mine Gas State Decision-Making System based on large language models (LLMs) a multi-agent system. The system aims to enhance over-limit alarms improve generating reports. integrates reasoning capabilities LLMs optimizes task allocation execution agents through study hybrid orchestration algorithm. Furthermore, establishes comprehensive risk assessment knowledge base, encompassing historical alarm data, real-time monitoring criteria, treatment methods, relevant policies regulations. Additionally, incorporates several technologies, including retrieval-augmented generation human feedback mechanisms, tool management, prompt engineering, asynchronous processing, which further application performance LLM status Experimental results indicate that effectively improves quality reports coal mines, providing solid technical support for accident prevention management mining operations.

Язык: Английский

Процитировано

1
A multi-agent-driven robotic AI chemist enabling autonomous chemical research on demand DOI Creative Commons
Tao Song, Man Luo, Linjiang Chen

и другие.

Опубликована: Июль 30, 2024

The successful integration of large language models (LLMs) into laboratory workflows has demonstrated robust capabilities in natural processing, autonomous task execution, and collaborative problem-solving. This offers an exciting opportunity to realize the dream chemical research on demand. Here, we report a robotic AI chemist powered by hierarchical multi-agent system, ChemAgents, based on-board Llama-3-70B LLM, capable executing complex, multi-step experiments with minimal human intervention. It operates through Task Manager agent that interacts researchers coordinates four role-specific agents—Literature Reader, Experiment Designer, Computation Performer, Robot Operator—each leveraging one foundational resources: comprehensive Literature Database, extensive Protocol Library, versatile Model state-of-the-art Automated Lab. We demonstrate its versatility efficacy six experimental tasks varying complexity, ranging from straightforward synthesis characterization more complex exploration screening parameters, culminating discovery optimization functional materials. Our multi-agent-driven showcases potential on-demand drive unprecedented efficiencies, accelerate discovery, democratize access advanced across academic disciplines industries.

Язык: Английский

Процитировано

3