用单次生成替代多阶段写作，让AI更高效写出结构严谨的论文引言。
Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning
- 将写作流程内化为单一策略，通过显式阶段标记控制
- 提升内容连贯性与结构合理性，推理效率更高
- 适合需要高质量引言生成的研究者和论文撰写工具
利用大语言模型（LLMs）生成严谨的论文引言仍具挑战，需协调背景、研究空白、方法与贡献之间的逻辑关系。现有方法将该过程外化为多阶段提示或代理工作流，成本高且易产生跨阶段偏差。本文提出 StructPO，一种结构感知的策略学习框架，将整个多阶段写作流程内化为单次通过的策略，由显式阶段标记控制。StructPO引入结构感知信用分配，解耦局部阶段质量与全局连贯性；采用精炼引导优化，将修改行为内化至首次生成策略中。实验表明，相比基于工作流的基线，StructPO在语义对齐、结构合理性与推理效率上均有提升，具备跨领域泛化能力，在人类评估中与 GPT-5.1 相当，且在缩放至 Qwen3-32B 时表现优异。结果表明，通过细粒度策略优化内化学术写作流程，是替代昂贵外部编排的有效方案。
原文摘要 · Abstract (English)
Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identification, method and contribution within a coherent narrative. Existing solutions externalize this process as multi-stage prompts or agent workflows which are expensive and vulnerable to cross-stage drift. We propose StructPO, a struct-aware policy learning framework that internalizes the entire multi-stage writing workflow into a single-pass policy controlled by explicit stage tokens. StructPO introduces struct-aware credit assignment to decouple local stage quality from global coherence and refinement-guided optimization to internalize revision behavior into the first-pass policy. 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. These results show that internalizing academic writing workflows through fine-grained policy optimization offers a viable alternative to costly external orchestration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。