arXiv cs.AI· Gunik Luthra, Ronald J. Pandolfi, Benjamin T. Diroll, Ricky Ronquillo, Ruipeng Li, Christopher B. Murray, Marcus M. Noack, Kevin G. Yager, Esther H. R. Tsai·· 2 小时前AI 评分54
可审计人机智能体团队自主完成同步辐射 X 射线实验
Auditable Human-Agent Teams for Autonomous X-ray Experimentation
AI 导读
研究团队基于编码智能体基础设施，在纳米粒子超晶格上演示了人在回路定义目标下的自主同步辐射 X 射线实验。三次实验中 61-67% 的消息涉及解释或判断，方法与科学贡献占比从 46% 升至 56-61%；溯源显示 59-68% 的错误纠正涉及多名参与者，约一半决策纳入了他人输入。完整的人机与智能体间对话记录支持决策溯源审计，可为多智能体科学系统设计提供参考。
正文 · 原文
Abstract:Closed-loop autonomous experimentation can accelerate scientific discovery, but implementation effort limits accessibility. Agentic systems may lower this barrier, although sustained operation on physical instruments remains largely unexplored. Here, using coding-agent infrastructure grounded in validated scientific methods, we demonstrate autonomous synchrotron X-ray experiments on nanoparticle superlattices under evolving, human-defined objectives. Complete human-agent and agent-agent transcripts enable an audit that reconstructs decision provenance and characterizes the division of cognitive labor. Across three experiments, 61-67% of messages involved interpretation or judgment, while the share of methodological and scientific contributions increased from 46% in the setup-focused first experiment to 56-61% in later experiments. Provenance showed that 59-68% of error corrections involved multiple participants and that about half of all decisions incorporated the input of another participant. These results may guide design principles for multi-agent scientific systems and inform future agent harnesses, model training, and accessible autonomous experimentation.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.12933 [cs.AI] |
| (or arXiv:2611.12933v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.12933 arXiv-issued DOI via DataCite |
Submission history
From: Esther Tsai [view email]
[v1]
Fri, 6 Nov 2026 08:33:55 UTC (11,456 KB)
来源：arXiv cs.AI · arxiv.org