arXiv cs.AI· Marko Petkovi\'c, Susanne Gooijer, Jos\'e Manuel Vicent-Luna, Vlado Menkovski, Sof\'ia Calero·· 12 小时前AI 评分34
RaspAssistant：面向多孔材料吸附模拟研究自动化的智能体框架
RaspAssistant as an Agentic Framework for Automating Adsorption Simulation Research in Porous Materials
AI 导读
RaspAssistant 是一个分层多智能体框架，可将多孔材料吸附研究从力场准备推进到验证与分离分析。在覆盖四个吸附与分离基准的十二次多智能体工作流复现运行中，总分在 8.50 至 10.00 之间；另一项八案例力场提取基准的平均加权得分为 0.967。在开放式研究中，该系统诊断并改进了乙炔力场，并在用 MFI 实验验证 CO₂ 力场后筛选了 197 种通过自动输入检查的纯硅沸石。
正文 · 原文
Abstract:Porous-material adsorption studies require coordinated structure preparation, force-field selection, simulation, validation, and interpretation, making end-to-end automation difficult. We test whether RaspAssistant, a hierarchical multi-agent framework, can carry an adsorption study from force-field preparation through validation and downstream separation analysis. Across twelve multi-agent workflow-reproduction runs spanning four adsorption and separation benchmarks, overall scores ranged from 8.50 to 10.00 on a rubric evaluating workflow correctness, simulation validity, and analysis consistency. In a separate eight-case force-field extraction benchmark, the mean weighted score was 0.967, combining parameter agreement and RASPA readiness. In open-ended studies, the system diagnosed and refined an acetylene force field and, after validating a CO$_2$ force field against MFI experiments, screened 197 pure-silica zeolites that passed automated input checks. These results demonstrate autonomous workflow execution after task specification and input provision: RaspAssistant coordinates, validates, adapts, and documents extended adsorption-simulation workflows while exposing model sensitivity and methodological limitations for expert review.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27572 [cs.AI] |
| (or arXiv:2610.27572v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27572 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Marko Petković [view email]
[v1]
Tue, 20 Oct 2026 03:41:00 UTC (1,836 KB)
来源：arXiv cs.AI · arxiv.org