Molecular LLM Agents: From Architectural Design to Scientific Autonomy
2026-08-24 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors explain how large language models (LLMs) can be used to work with molecules, which are more complex than just text or code because they involve 3D shapes, chemical data, and lab experiments. They present a framework describing how these molecular LLM agents should be built, focusing on how they perceive molecules, use tools, and learn. They also introduce a scale with four levels showing how much independence these agents have, from simple helpers to fully autonomous scientific planners. Their work helps compare current molecular LLM agents and guides future development in this field.
large language modelmolecular representationmolecular graphs3D conformationchemical perceptionagent frameworktool groundingscientific autonomymolecular discovery
Authors
Jiatong Li, Wengyu Zhang, Weida Wang, Yuxuan Ren, Wei Liu, Chenyang Mao, Yuqiang Li, Yatao Bian, Changmeng Zheng, Xiaoyong Wei, Qing Li
Abstract
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.