Dewu Zheng

Critical tokens can make or break code generation, and ACToR ensures they receive the precise context needed to succeed.

PTA-IRT reveals that incorporating detailed problem-solving trajectories can dramatically enhance the evaluation accuracy of software engineering agents.

Mainstream LLMs miss 40% of defects in multi-round code reviews, revealing their limitations in real-world software development contexts.

Training on just 10% of carefully curated trajectories can lead to performance improvements of over 24% in software issue resolution tasks.