Yun Peng

Coding agents are failing to meet user requests, with a mere 31.5% success rate, highlighting a critical gap in requirement recovery that must be addressed.

Models can identify abstract structures in isolation but fail dramatically when asked to translate that understanding across different contexts, revealing a critical gap in AI's reasoning abilities.

EffiHolmes achieves a remarkable 15% improvement in function-level accuracy for time inefficiency localization, setting a new standard in the field.

Rule-based defenses may protect LLMs while preserving task performance, but many popular methods compromise usability and efficiency.

Achieving up to 3.97x speedup in human-written code, Optimo redefines how we optimize dynamic languages by employing a multi-level approach that outperforms traditional methods.

Resolve rates mask critical insights about coding agent performance, but TraceProbe uncovers the hidden trajectory structures that explain why some runs succeed while others fail.