Supervising Ralph Wiggum: Exploring a Metacognitive Co-Regulation Agentic AI Loop for Engineering Design

Researchers developed a novel Co-Regulation Design Agentic Loop (CRDAL) system that uses metacognitive agents to improve AI-driven engineering design by reducing design fixation. The system showed better performance than traditional approaches in battery pack design tasks without significantly increasing computational costs.

• →CRDAL system uses a Metacognitive Co-Regulation Agent to assist design agents in overcoming fixation on existing paradigms.
• →The system generated better-performing battery pack designs compared to Ralph Wiggum Loop and Self-Regulation Loop approaches.
• →CRDAL navigated the latent design space more effectively than baseline methods without major computational overhead.
• →Self-Regulation Loop alone did not significantly improve performance despite exploring different design regions.
• →The research provides practical frameworks for developing more effective agentic AI systems in engineering applications.