Divergent strategies and convergent outcomes in autonomous materials discovery

2026-09-20

AI Summary

研究通过16个自主科学代理在限定条件下探索金属有机框架材料，尽管策略不同但结果趋同，揭示了共享输入导致的稳健结论和共模错误。

Abstract

Scientific agents are mostly evaluated on whether they complete tasks or recover known results; we instead study variation across repeated open-ended campaigns. Sixteen separately initialized sessions of one model-harness configuration received a frozen database of 12,499 metal-organic frameworks, a methane-storage objective, a pinned protocol and a one-week budget. Strategies diverged into four approaches spanning 100--5,000 screened structures, and eight built 2,253 hypothetical structures. Yet the agents recovered the same materials frontier near 200 cm^3/cm^3, and an independent calculation of the database's porous region found its nine best structures all among their reports. Enforced checks on half the agents raised fresh-run reproduction from one of eight to eight of eight but could not detectably improve conclusion validity, because fifteen of sixteen agents selected the same audit-excluded entry, an incomplete structure whose missing anions created artificial pore volume. Replicated agents thus reveal both robust conclusions and common-mode errors from shared inputs.

Problem

• autonomous materials discovery
• divergent strategies
• convergent outcomes
• common-mode errors

Innovation

• autonomous materials discovery
• divergent strategies
• convergent outcomes
• reproducibility checks
• common-mode errors