Chenyue Zhou

LLMs that ace one-shot optimization problems often stumble when faced with the messy reality of iterative model building, revision, and explanation in industrial settings.

Evaluating web coding LLMs with real-world fidelity reveals that even state-of-the-art models still struggle with aesthetics and framework-specific nuances.

LLM agent progress increasingly hinges on better external cognitive infrastructure, not just stronger models.