A survey of agentic materials science and engineering: where are we and where are we going?

Agents mostly built upon large language models (LLMs) with planning, tool-use, memory, and self-reflection capabilities are revolutionizing all aspects of materials science and engineering (MSE), from materials design, experiment execution, industrial manufacture, to deployment, thereby opening the age of agentic MSE. Rather than isolated AI predictive models, these agents coordinate multi-step scientific workflows by retrieving and structuring knowledge, proposing and refining hypotheses, planning experiments, combining multi-modal simulations and characterizations, and, when integrated with AI materials laboratories, closing the loop toward autonomous discovery of materials. However, agentic systems exhibit varying degrees of autonomy, and their roles in materials research and development differ accordingly. To systematically examine the landscape of agentic MSE, this survey proposes a six-level autonomy framework (Levels 0-5) that characterizes the progression from human-only workflows to fully autonomous scientific agents. The framework aligns with key task families across all steps in MSE, including information retrieval, property prediction, simulation, synthesis, and characterization. By reviewing recent advances in agentic MSE, we reveal uneven progress. Knowledge-centric capabilities often remain early-stage, while experimental orchestration and characterization are starting to explore higher-level agent behaviors. Importantly, mature autonomy requires coordinating multiple tasks rather than optimizing a single one. Collectively, these insights provide a structured roadmap for advancing agentic MSE toward higher autonomy.