Comparison between a human research community and an autonomous AI network. (a) Researchers in different fields form a researcher network by sharing extensive knowledge through communication, and advance exploration of new materials. (b) Autonomous AI systems exploring different materials form an autonomous AI network by spontaneously sharing knowledge, and advance exploration of new materials. Credit: npj Computational Materials (2025). DOI: 10.1038/s41524-025-01851-8

A joint research team from NIMS and University of Tsukuba have developed an autonomous AI network technology that allows multiple autonomous AI systems to efficiently discover new materials by spontaneously collaborating with each other and forming a network. The team demonstrated the effectiveness of the technology through simulations. The research was published in npj Computational Materials on December 9, 2025.

Challenges in current AI systems

In recent years, autonomous AI systems that integrate artificial intelligence (AI), robotics, and simulations have attracted attention and have been built and operated worldwide. However, current autonomous AI systems operate in isolation, without collaborating with other systems. This is because the AI systems explore different material systems, and while they can share data easily, it is challenging for them to utilize data from other systems in their own autonomous exploration.

Human researchers advance research in a sophisticated manner while sharing extensive knowledge by forming research communities through conversation (see the left side of the above image). Likewise, if multiple autonomous AI systems can perform autonomous exploration while sharing and utilizing extensive knowledge (trends extracted from data) by forming a network, they can discover new materials more efficiently.

Developing collaborative AI networks

In this research, the team took a hint from human research communication methods to develop an autonomous AI network technology by which multiple autonomous AI systems collaborate to perform autonomous exploration while sharing knowledge. In a research community, a human researcher normally does not merely give their research data to another researcher, but communicates by way of conveying some knowledge gained from that data to the other researcher.

In order to realize this also among autonomous AI systems, the research team built an algorithm that incorporates knowledge learned by other systems as a reference for decision-making, and enabled the AI systems to perform autonomous exploration while sharing knowledge instead of data.

Results and future outlook

As shown on the right side of the above image, when three autonomous AI systems, each performing exploration to maximize a different physical property value, were made to spontaneously exchange knowledge with each other, their optimization speed was found to improve. In other words, the team demonstrated that the exploration efficiency of each system improves by forming an autonomous AI network.

Autonomous AI systems that integrate AI, robotics, and simulations have been developed worldwide, and are constantly performing material exploration. Their number will continue to increase rapidly, and various types of autonomous AI systems will discover and synthesize numerous new materials.

This large number of autonomous AI systems has the potential to generate greater value by collaborating with each other in the future. Going forward, the team aims to build a more enormous autonomous AI network, while further advancing development of autonomous AI systems.

Publication details

Naoki Yoshida et al, Networking autonomous material exploration systems through transfer learning, npj Computational Materials (2025). DOI: 10.1038/s41524-025-01851-8

Citation: Multiple autonomous AI systems spontaneously collaborate to advance materials research (2026, January 20) retrieved 20 January 2026 from https://phys.org/news/2026-01-multiple-autonomous-ai-spontaneously-collaborate.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.