arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.02484cs.AIcs.LGcs.MAphysics.chem-ph
收藏

El Agente:一种用于量子化学的自主智能体

El Agente: An Autonomous Agent for Quantum Chemistry

University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究院);Canadian Institute for Advanced Research (CIFAR)(加拿大高级研究院);Acceleration Consortium(加速联盟);NVIDIA(英伟达)
Yunheng Zou, Austin H. Cheng, Abdulrahman Aldossary, Jiaru Bai, Shi Xuan Leong, Jorge Arturo Campos-Gonzalez-Angulo, Changhyeok Choi, Cher Tian Ser, Gary Tom, A… 展开作者

Yunheng Zou, Austin H. Cheng, Abdulrahman Aldossary, Jiaru Bai, Shi Xuan Leong, Jorge Arturo Campos-Gonzalez-Angulo, Changhyeok Choi, Cher Tian Ser, Gary Tom, Andrew Wang, Zijian Zhang, Ilya Yakavets, Han Hao, Chris Crebolder, Varinia Bernales, Alán Aspuru-Guzik

AI总结:

提出基于LLM的多智能体系统El Agente Q,通过分层记忆架构动态生成并执行量子化学工作流,在基准测试中实现超87%成功率,支持多步骤任务与原位调试,提升了量子化学的自主性与可访问性。

摘要:

计算化学工具被广泛用于研究化学现象的行为。然而,这些工具的复杂性使其对非专家而言难以使用,甚至对专家也具有挑战性。在本研究中,我们提出了El Agente Q,这是一个基于LLM的多智能体系统,能够根据自然语言用户提示动态生成并执行量子化学工作流。该系统构建于一种新颖的认知架构之上,具有分层记忆框架,可实现灵活的任务分解、自适应工具选择、后分析,以及自主的文件处理与提交。El Agente Q在六道大学水平课程练习和两个案例研究上进行了基准测试,展现出稳健的问题解决性能(平均任务成功率>87%),并通过原位调试实现了自适应错误处理。它还支持更复杂工作流的长期、多步骤任务执行,同时通过详细的动作追踪日志保持透明度。这些能力共同为日益自主和可访问的量子化学奠定了基础。

英文摘要:

Computational chemistry tools are widely used to study the behaviour of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging >87% task success) and adaptive error handling through in situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑