发表机构
Shanghai Artificial Intelligence Laboratory; Zhejiang University; Tsinghua University; Harbin Institute of Technology; Shanghai Jiao Tong University; The Chinese University of Hong Kong; Fudan University; Wuhan University; Beihang University; Renmin University of China（上海人工智能实验室; 浙江大学; 清华大学; 哈尔滨工业大学; 上海交通大学; 香港中文大学; 复旦大学; 武汉大学; 北京航空航天大学; 中国人民大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RoboChemGym提出协议驱动的生成式仿真框架，通过自我改进任务合成机制，自动生成符合真实化学实验协议的高保真操作示范，并引入分层基准评估，以解决长时程化学操作中训练数据稀缺的问题。
AI 中文摘要
湿实验室实验是科学发现中假设验证的金标准，但其本质上劳动密集、成本高昂且涉及安全关键问题。具身智能体有望自动化这些繁琐的工作流程，但其发展受到真实世界训练数据稀缺的阻碍。虽然仿真为生成示范提供了可扩展的替代方案，但当前方法主要针对相对短时程的任务，且交互结构松散，无法满足化学实验的严格程序约束和精细操作需求。为弥合这一差距，我们引入了RoboChemGym，一个能够自主生成与真实实验协议对齐的高保真操作示范的框架，其特点是具有自我改进的任务合成机制，可迭代优化任务执行和场景配置，从而能够可靠地为超过10个交互步骤的复杂多对象协议生成专家轨迹。此外，我们引入了一个分层基准，系统性地评估不同粒度下的性能，涵盖从原子操作到全周期实验工作流程。RoboChemGym为复杂化学任务中具身智能体的自动化数据合成和能力评估树立了可扩展的范式，为迈向全智能实验室迈出了关键一步。
英文摘要
Wet-lab experimentation serves as the gold standard for hypothesis verification in scientific discovery; yet it is inherently labor-intensive, costly, and safety-critical. Embodied agents hold the promise of automating these tedious workflows, but their development is hindered by the scarcity of real-world training data. While simulation offers a scalable alternative for producing demonstrations, current methods primarily target relatively short-horizon tasks with loosely structured interactions, failing to meet the strict procedural constraints and fine-grained manipulation demands of chemical experiments. To bridge this gap, we introduce \textbf{RoboChemGym}, a framework that autonomously generates high-fidelity manipulation demonstrations aligned with real-world experiment protocols, featuring a \textit{self-improving task synthesis} mechanism to iteratively refine task execution and scene configurations, enabling the reliable generation of expert trajectories for complex, multi-object protocols exceeding 10 interaction steps. Furthermore, we introduce a hierarchical benchmark that systematically assesses performance across varying granularities, spanning from atomic operations to full-cycle experimental workflows. RoboChemGym sets a scalable paradigm for the automated data synthesis and capability evaluation of embodied agents in intricate chemical tasks, serving as a critical stepping stone toward fully intelligent laboratories.
