摘要：随着来自高通量平台或计算研究的分子数据库日益普及，化学领域近期进入了高数据量时代。化学科学内部不断提升的自动化正在推动更具数字化与精准化的化学发展。专用的科学智能体（Scientific Agents）在引导化学家应对不断增长的数据和研究发现（包括负面结果）方面正变得愈发关键。在此，我们推出了 Magnolia——一个基于大语言模型（LLM）的持久记忆人工智能 Agent 框架，它整合了从分子对接、量子化学等计算协议，到实验记录本与对话日志的各项内容。该框架依托于一套三层记忆系统：自动捕捉会话层级的观察结果并将其提炼为结构化认知，经确认后升格为项目层级条目，并在经人工验证后晋升为跨项目规则，从而主动指导后续工作并提供直接的化学反馈。我们在四个案例研究中展示了 Magnolia 的能力：芳香系统的量子化学评估（COMPAS 数据库）、丁烷与修饰 DNA 的分子动力学模拟，以及一项蛋白质-多肽对接研究。在这些项目中，Magnolia 共追踪了 317 次运行并积累了 116 个项目级条目，从中沉淀出 4 条跨项目规则；在对四项任务进行的受控重放测试中，具备记忆的运行成功通过了无记忆运行失败的检查（例如，对接配置检查通过率达到 10/10，而无记忆对照组仅为 1 到 4/10）。通过将自动化、可复现性与人机协同（Human-in-the-loop）控制相结合，我们的 Magnolia 框架利用直接分析与 LLM 增强反馈，有效简化了分子对接、分子动力学及量子化学计算流程，为加速开展计算（生物）化学研究提供了全新路径。

Abstract:Chemistry has recently entered a high-data regime as molecular databases from high-throughput platforms or computational studies have become available. Increasing automation within the chemical sciences leads to a more digital and precision chemistry. Dedicated scientific agents are becoming central to guiding the chemist through an ever-increasing amount of data and findings, including negative ones. Here, we introduce Magnolia, a persistent-memory artificial intelligence agent framework that integrates computational protocols, from docking to quantum chemistry, lab notebooks and chat logs relying on large language models (LLMs). It relies on a three-tier memory system: session-level observations are automatically captured and distilled into structured learnings, confirmed and elevated to project-tier entries and, when human-validated, promoted to cross-project rules that actively guide subsequent work and provide direct chemical feedback. We illustrate Magnolia on four case studies: quantum-chemical evaluation of aromatic systems (COMPAS database), molecular dynamics of butane and of modified DNA, and a protein-peptide docking campaign. Across these projects, Magnolia tracked 317 runs and accumulated 116 project-tier entries, from which four cross-project rules were promoted; in controlled replays of four tasks, runs with memory passed the checks that runs without it failed (for example, ten of ten docking-configuration checks, against one to four of ten). By combining automation, reproducibility, and human-in-the-loop control, our Magnolia framework streamlines docking, molecular dynamics and quantum chemistry calculations with direct analysis and LLM-augmented feedback, offering accelerated access to computational (bio)chemistry.