Jie M. Zhang
3 papers · Latest:
Software Engineering
StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
StepCodeReasoner uses RL to align code reasoning with stepwise execution traces, achieving SOTA performance by supervising intermediate states.
2605.11922
Software EngineeringLLMs Are Not a Silver Bullet: A Case Study on Software Fairness
A study finds traditional ML methods consistently outperform LLMs for software fairness and predictive performance, challenging LLMs' utility in this domain.
2604.12640
Software EngineeringSkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
SkillMOO optimizes LLM agent skill bundles for software engineering, boosting pass rates by 131% and cutting costs by 32% through automated evolution.
2604.09297
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.