Zhihao Lin

LLM agents can restore compatibility in over 60% of outdated repositories, but their effectiveness varies dramatically based on the complexity of the required changes.

Execution in LLM-based program repair is often a costly default that yields minimal benefits, suggesting a need for a strategic reevaluation of its use.

Lightweight structural annotations can enhance code agent navigation by improving localization and stability, transforming stochastic exploration into a more disciplined process.

Generated translation references outperform ground truth by 8.65 CEA100 points, showcasing a novel approach to literary translation challenges.