分子大语言模型智能体：从架构设计到科学自主性
Molecular LLM Agents: From Architectural Design to Scientific Autonomy
浏览论文内容
中文总结 AI 辅助
该研究提出分子LLM智能体的概念框架，从架构设计和科学自主性阶梯两方面展开，为分子领域LLM智能体的比较、设计评估及部署提供指导。
中文摘要 AI 辅助
分子科学是基于大语言模型（LLM）的智能体的重要前沿领域。与主要在自然语言、代码或网络环境中运行的通用智能体不同，分子LLM智能体必须对化学对象进行感知、推理和操作，这些化学对象涵盖符号字符串、分子图、3D构象、光谱、模拟以及湿实验室测量结果。其能力依赖于符合化学原理的分子感知、以LLM为核心的智能体框架、特定领域的工具接地，以及计算或实验反馈，此外还包括规划和工具使用能力。本研究从两个互补视角开发了分子LLM智能体的概念框架：其一，介绍分子智能体设计的架构视角，涵盖分子表示与感知、智能体框架、特定领域工具箱，以及学习与优化；其二，提出受工程系统分阶段自主性启发的科学自主性阶梯，将智能体分为四个级别：L1辅助或固定工作流、L2自适应计算智能体、L3感知反馈的物理实验智能体、L4科学议程智能体。这两个视角共同构建了一个综合框架，用于比较现有分子LLM智能体、识别缺失的能力与部署风险，并指导分子发现工作流中未来智能体的设计、评估与部署。
英文摘要
Molecular science represents an important frontier for LLM-based agents. Unlike general agents that mainly operate over natural language, code, or web environments, molecular LLM agents must perceive, reason about, and act upon chemical objects across symbolic strings, molecular graphs, 3D conformations, spectra, simulations, and wet-lab measurements. Their capabilities depend on chemically faithful molecular perception, an LLM-centered agent framework, domain-specific tool grounding, and computational or experimental feedback, in addition to planning and tool use. This work develops a conceptual framework for molecular LLM agents from two complementary perspectives. First, we introduce an architectural view of molecular-agent design, covering molecular representation and perception, the agent framework, domain-specific toolboxes, and learning and optimization. Second, we propose a scientific autonomy ladder inspired by staged autonomy in engineering systems, categorizing agents into four levels: L1 assistive or fixed workflows, L2 adaptive computational agents, L3 feedback-aware physical experiment agents, and L4 scientific-agenda agents. Together, these two perspectives establish a comprehensive framework for comparing existing molecular LLM agents, identifying missing capabilities and deployment risks, and guiding the design, evaluation, and deployment of future agents in molecular discovery workflows.
发表机构
- The Hong Kong Polytechnic University（香港理工大学）
- Shanghai AI Lab（上海人工智能实验室）
- National University of Singapore（新加坡国立大学）
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
