2 papers
cs.SE2026
Refine After Generation: Toward Correct and Concise Patches in LLM-based Program Repair
Wenqiang Luo, Jacky Keung, Xiaoyu Shi +4
Large language models (LLMs) have advanced automatic program repair (APR) to the point where agentic systems routinely resolve real-world, repository-level issues. Yet the generate…
cs.LG2026
Revisiting Overestimation Bias Problem of Q-learning: Settling Large Discrete Action Space via Action Intersection
Pu Li, Tao Tan, Hong Xie +2
This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods. We find…