Scholarlink

<p>Chemputation is the process of programming chemical robots to do experiments using a universal symbolic language, but literature can be error-prone and hard to read due to ambiguities. Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, including natural language processing, robotic control, and more recently, chemistry. Despite significant advancements in standardizing synthetic chemistry data, automatic reproduction and verification of reported syntheses remains labor-intensive task. We introduce an LLM-based chemical research agent workflow for automatic verification of synthetic literature procedures. Our workflow can autonomously extract synthetic procedures and analytical data from extensive documents, translate these procedures into universal <i>X</i>DL code, simulate the execution in a hardware-specific setup, and ultimately execute the procedure on an <i>X</i>DL-controlled robotic system for synthetic chemistry to confirm the procedure works in the real world. This demonstrates the potential of LLM-based workflows for autonomous chemical synthesis with Chemputers. While recent LLM-based agents have demonstrated remarkable success in autonomous experiment planning, a robust workflow for the faithful digitization and verification of existing literature remains a challenge. Our approach bridges this gap by providing six realistic examples of syntheses directly executed from synthetic literature on two robotic platforms. Our workflow will significantly enhance automation in robotically driven synthetic chemistry research, streamline data extraction, improve the reproducibility, scalability, and safety of synthetic chemistry.</p><p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Verification and execution of the scientific literature via chemputation augmented by large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月3日

查看全文
  • Sebastian Pagel,
  • Michael Jirasek,
  • Leroy Cronin

摘要

Chemputation is the process of programming chemical robots to do experiments using a universal symbolic language, but literature can be error-prone and hard to read due to ambiguities. Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, including natural language processing, robotic control, and more recently, chemistry. Despite significant advancements in standardizing synthetic chemistry data, automatic reproduction and verification of reported syntheses remains labor-intensive task. We introduce an LLM-based chemical research agent workflow for automatic verification of synthetic literature procedures. Our workflow can autonomously extract synthetic procedures and analytical data from extensive documents, translate these procedures into universal XDL code, simulate the execution in a hardware-specific setup, and ultimately execute the procedure on an XDL-controlled robotic system for synthetic chemistry to confirm the procedure works in the real world. This demonstrates the potential of LLM-based workflows for autonomous chemical synthesis with Chemputers. While recent LLM-based agents have demonstrated remarkable success in autonomous experiment planning, a robust workflow for the faithful digitization and verification of existing literature remains a challenge. Our approach bridges this gap by providing six realistic examples of syntheses directly executed from synthetic literature on two robotic platforms. Our workflow will significantly enhance automation in robotically driven synthetic chemistry research, streamline data extraction, improve the reproducibility, scalability, and safety of synthetic chemistry.