Xiaocheng Yang

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.

Agents struggle to maintain planning accuracy in complex tool ecosystems, with GPT-5.4's performance plummeting from 51.90% to 11.36% under severe blocking conditions.