让AI写作像人一样灵活调整思路，动态拆解任务。
Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models
- 通过递归分解与执行交织的规划机制，打破固定写作流程限制。
- 在小说和报告生成中均超越现有方法，各项自动指标领先。
- 适合需要自适应长文生成的研究者与开发者使用。
长篇写作代理需要在信息检索、推理与创作之间实现灵活集成与交互。当前方法依赖预设工作流和僵化思维模式，在写作前生成大纲，导致写作过程适应性受限。本文提出WriteHERE，一种通用代理框架，通过递归任务分解与动态融合三种基本任务类型（检索、推理、创作），实现类人的自适应写作。方法包含：1）将递归任务分解与执行交织的规划机制，消除写作流程的人工限制；2）任务类型的动态整合，支持异构任务分解。在小说写作与技术报告生成任务上的评估表明，该方法在所有自动评价指标上持续优于现有最先进方法，验证了框架的有效性与普适性。代码与提示已公开，以促进后续研究。
原文摘要 · Abstract (English)
Long-form writing agents require flexible integration and interaction across information retrieval, reasoning, and composition. Current approaches rely on predefined workflows and rigid thinking patterns to generate outlines before writing, resulting in constrained adaptability during writing. In this paper we propose WriteHERE, a general agent framework that achieves human-like adaptive writing through recursive task decomposition and dynamic integration of three fundamental task types: retrieval, reasoning, and composition. Our methodology features: 1) a planning mechanism that interleaves recursive task decomposition and execution, eliminating artificial restrictions on writing workflow; and 2) integration of task types that facilitates heterogeneous task decomposition. Evaluations on both fiction writing and technical report generation show that our method consistently outperforms state-of-the-art approaches across all automatic evaluation metrics, demonstrating the effectiveness and broad applicability of our proposed framework. We have publicly released our code and prompts to facilitate further research.
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。