A cold-start self-evolving multi-agent intelligence for closed-loop prediction from materials synthesis to performance

Large language models (LLMs) are increasingly used to propose materials and plan experiments1–3, but whether they can predict previously unreported syntheses and the structures and performance of the resulting products before experimental validation remains unclear. Here we test this capability using a multi-agent framework of general-purpose, unfine-tuned LLMs that enables cross-disciplinary collaboration, with an AI scientist coordinating chemistry, materials science and electrochemistry agents to performance closed-loop predictions of the reaction process, crystal phase and battery performance of TiO2 anodes synthesized by a previously unreported rapid Joule-heating route. The agents predicted 64 conditions blind in eight rounds and, after each round, rewrote natural-language Skills from the released measurements. A task-matched team predicted the reaction process and phase in 91.7% and 82.8% accuracy, with errors concentrated near sharp transitions, whereas quantitative predictions of rate-capability and long-cycle performance achieved accuracies of 59.2% (72.3% for anatase-rich products) and 68.1%, within ±30% of experimental values. Revised Skills raised accuracy on identical conditions in most matched tests, and rewriting Skills without new measurements did not. A complete prediction chain cost ~US$0.27 per condition. These results indicate that LLM predictions could replace exploratory trials under conditions far away from sharp transitions, pointing to a prediction-first research paradigm.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-18
DOI
https://doi.org/10.21203/rs.3.rs-11771581/v1
Primary Topic
Machine Learning in Materials Science
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

A cold-start self-evolving multi-agent intelligence for closed-loop prediction from materials synthesis to performance

Kunlei Zhu, Yingxue Ren, Shaoqi Mao, Xueyang Cheng et al.
7 links
Research Square
Machine Learning in Materials Science
preprint

A cold-start self-evolving multi-agent intelligence for closed-loop prediction from materials synthesis to performance

Kunlei Zhu, Yingxue Ren, Shaoqi Mao, Xueyang Cheng, Tao Li, Shimiao Sun
preprint en

Abstract

Large language models (LLMs) are increasingly used to propose materials and plan experiments1–3, but whether they can predict previously unreported syntheses and the structures and performance of the resulting products before experimental validation remains unclear. Here we test this capability using a multi-agent framework of general-purpose, unfine-tuned LLMs that enables cross-disciplinary collaboration, with an AI scientist coordinating chemistry, materials science and electrochemistry agents to performance closed-loop predictions of the reaction process, crystal phase and battery performance of TiO2 anodes synthesized by a previously unreported rapid Joule-heating route. The agents predicted 64 conditions blind in eight rounds and, after each round, rewrote natural-language Skills from the released measurements. A task-matched team predicted the reaction process and phase in 91.7% and 82.8% accuracy, with errors concentrated near sharp transitions, whereas quantitative predictions of rate-capability and long-cycle performance achieved accuracies of 59.2% (72.3% for anatase-rich products) and 68.1%, within ±30% of experimental values. Revised Skills raised accuracy on identical conditions in most matched tests, and rewriting Skills without new measurements did not. A complete prediction chain cost ~US$0.27 per condition. These results indicate that LLM predictions could replace exploratory trials under conditions far away from sharp transitions, pointing to a prediction-first research paradigm.

Research Square
Qufu Normal University (CN)
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon