Abdulrahman AlRabah

When faced with noisy tools, state-of-the-art LLMs fail to prevent educators from over-relying on incorrect suggestions, exposing a significant flaw in AI decision support.

Fine-grained credit assignment in multi-agent systems can dramatically boost performance, revealing error sources with unprecedented precision.

Unlock personalized learning at scale with InstructKG, which automatically builds knowledge graphs from lecture materials to map out learning dependencies, revealing student knowledge gaps.