HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

Weiqi Wang and co-authors submitted the paper "HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning" to arXiv on January 30, 2026, with a revised version posted on July 9, 2026. The paper is categorized under cs.LG and cs.CL. It was assigned an arXiv-issued DOI via DataCite and is available in PDF and HTML formats.