Felix Gehlhoff

LLM agents can significantly enhance fault recovery in process plants by intelligently suggesting actions that are validated before execution, reducing reliance on human operators.

Engineers can now automate PDDL generation from AAS models, eliminating the need for specialized planning knowledge and enabling systematic design exploration.

LLMs can make formal planning tools actually usable in messy real-world industrial settings by translating solver outputs into actionable insights and adapting knowledge models on the fly.