Preprint
Aug 2026
Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning
Experiments show that StructPO improves semantic alignment, structural rationality and inference efficiency over workflow-based baselines, generalizes to out-of-domain settings, and remains competitive with GPT-5.1 in human evaluation when scaled to Qwen3-32B.
Meicong Zhang, Tiancheng Su, Jia-Hao Cheng et al.
· 0 citations