Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models

2025-03-11

AI Summary

Existing long-form writing agents rely on predefined outlines and rigid pipelines, resulting in inflexible coordination among information retrieval, reasoning, and generation—compromising adaptability and fidelity to human writing styles. This paper proposes an agent framework for long-text generation that abandons static planning in favor of a novel heterogeneous recursive planning mechanism. It enables dynamic, real-time re-decomposition and seamless integration across retrieval, reasoning, and writing tasks. Leveraging language-model-driven recursive task decomposition, adaptive workflow scheduling, and cross-task joint modeling, the framework achieves end-to-end adaptability. Evaluated on novel writing and technical report generation, it consistently surpasses state-of-the-art methods across all automated metrics—demonstrating superior effectiveness, generalizability, and stylistic consistency with human-authored texts.

Technology Category

• Natural Language Processing: Generation
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Long-form writing agents require flexible integration and interaction across information retrieval, reasoning, and composition. Current approaches rely on predetermined workflows and rigid thinking patterns to generate outlines before writing, resulting in constrained adaptability during writing. In this paper we propose a general agent framework that achieves human-like adaptive writing through recursive task decomposition and dynamic integration of three fundamental task types, i.e. 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, which demonstrate the effectiveness and broad applicability of our proposed framework.

Problem

• Enhances adaptability in long-form writing with language models.
• Overcomes rigid workflows in current writing agent approaches.
• Integrates retrieval, reasoning, and composition for dynamic task decomposition.

Innovation

• Recursive task decomposition for adaptive writing
• Dynamic integration of retrieval, reasoning, composition
• Planning mechanism eliminating rigid workflow restrictions