$\pi^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models.

arXiv:2604.05114v2 Announce Type: replace-cross Abstract: We study a QA curation pipeline for improving long-context complex reasoning in large language models (LLMs). Our approach, $\pi^2$, constructs high-quality reasoning data through rigorous QA curation: