Research Index

A novel framework combining metacognitive assessment capabilities with retrieval-augmented generation (RAG) for creating more reliable healthcare AI assistants. The system continuously evaluates its own knowledge limitations and uncertainty while building an evolving knowledge graph of medical information, enabling more trustworthy clinical decision support.

Applying LLM metacognition principles to improve power grid stability through intelligent Dynamic Voltage Restorer (DVR) control. The system combines uncertainty-aware decision making from medical LLMs with fast terminal sliding mode control for robust, self-aware power quality management.

A novel framework for developing embodied AI agents with true metacognitive capabilities by combining insights from medical LLM metacognition research with embodied learning. The system uses multi-modal feedback loops and real-world interaction data to teach robots when to act, when to ask for help, and how to recognize their own limitations.

A novel framework combining LLM metacognition capabilities with distributed microgrid control systems to enhance power grid resilience. The system uses uncertainty quantification from LLMs to make robust decisions about power distribution and load balancing, while incorporating real-time sensor data and weather forecasts.

A novel framework combining reinforcement learning with knowledge graphs to train LLMs in healthcare to develop accurate metacognitive abilities. The system learns to calibrate confidence levels, recognize knowledge boundaries, and identify situations requiring human intervention through iterative self-evaluation and external validation.