用智能体闭环系统自动纠错，高效找到催化表面吸附构型最低能量态。
AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces
- 构建多智能体框架，通过机器学习力场反馈实现自主纠错。
- 在两个基准测试中成功率高达100%和98.8%，仅需4.11~4.67次力场松弛。
- 相比传统方法减少约14倍计算量，且避免能量符号错误，适合自动化催化研究。
确定异相催化表面吸附物的最低能量构型对模拟至关重要，但基于从头算的全面探索计算成本过高。机器学习力场（MLFF）虽可加速结构弛豫，但对庞大构型空间的搜索仍是主要瓶颈；开环大语言模型（LLM）智能体缺乏物理基础的反馈机制，无法纠正初始误判。本文提出AdsMind（基于机器智能与弛豫反馈的吸附构型发现），一个闭环多智能体系统，通过MLFF弛豫反馈实现自主纠错。在四个LLM后端上，AdsMind在AA20和OCD-GMAE62基准测试中分别达到100%和98.8%的高成功率。相比单次运行（1-Shot）消融版本，其跨后端能量离散度降低，每例仅需4.11和4.67次MLFF弛豫——相较启发式枚举基线减少约14倍。使用VASP/PBE进行密度泛函理论验证，在六个代表性AA20体系中，开环吸附智能体输出对分子吸附物存在定性能量符号错误，而AdsMind在所有测试案例中均保持正确符号，并具有更优的定量一致性。因此，AdsMind同时实现可靠性、自我反思与可解释性，支持更受DFT指导的自动化化学工作流。
原文摘要 · Abstract (English)
Identifying the lowest-energy surface-adsorbate configuration is critical for modeling heterogeneous catalysis, yet exhaustive exploration with ab initio calculations is computationally prohibitive. Machine-learning force fields (MLFFs) accelerate structural relaxation but leave the search over the vast configurational space a major bottleneck, and open-loop large language model (LLM) agents lack a physics-grounded feedback mechanism to correct erroneous initial guesses. We propose AdsMind (Adsorption configuration discovery with Machine intelligence and relaxation feedback), a closed-loop multi-agent framework that enables autonomous error correction through MLFF relaxation feedback. Across four LLM backends, AdsMind achieves consistently high search reliability, with success rates of 100% and 98.8% on the benchmarks AA20 and OCD-GMAE62. Relative to its single-pass (1-Shot) ablation it reduces cross-backend energy dispersion, and it uses only 4.11 and 4.67 MLFF relaxations per case, respectively -- an approximately 14-fold reduction over heuristic enumeration baselines. Density functional theory (DFT) validation using VASP/PBE on six representative AA20 systems shows that the reported open-loop Adsorb-Agent outputs exhibit qualitative adsorption-energy sign errors for molecular adsorbates, whereas AdsMind preserves the correct sign in all tested cases with closer quantitative agreement. AdsMind thus delivers reliability, self-reflection, and interpretability simultaneously, supporting more DFT-informed autonomous chemistry workflows.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。