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

arXiv: https://arxiv.org/abs/2503.08275 · HTML: https://mlsanity.com/paper/2503.08275/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [ADaPT: As-Needed Decomposition and Planning with Language Models](https://mlsanity.com/paper/2311.05772/) (2023)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence](https://mlsanity.com/paper/2407.07061/) (2024)
- [StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows](https://mlsanity.com/paper/2403.11322/) (2024)
- [ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates](https://mlsanity.com/paper/2502.06772/) (2025)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models](https://mlsanity.com/paper/1511.09249/) (2015)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [Joint Prompt Optimization of Stacked LLMs using Variational Inference](https://mlsanity.com/paper/2306.12509/) (2023)
- [One Big Net For Everything](https://mlsanity.com/paper/1802.08864/) (2018)

## Built on by (most cited first, 16 of 16)

- [WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research](https://mlsanity.com/paper/2509.13312/) (2025)
- [Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2505.11277/) (2025)
- [Synergizing RAG and Reasoning: A Systematic Review](https://mlsanity.com/paper/2504.15909/) (2025)
- [EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes](https://mlsanity.com/paper/2509.00877/) (2025)
- [RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://mlsanity.com/paper/2511.18743/) (2025)
- [MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems](https://mlsanity.com/paper/2605.28732/) (2026)
- [ROMA: Recursive Open Meta-Agent Framework for Long-Horizon Multi-Agent Systems](https://mlsanity.com/paper/2602.01848/) (2026)
- [LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability](https://mlsanity.com/paper/2510.24345/) (2025)
- [ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research](https://mlsanity.com/paper/2606.20122/) (2026)
- [ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence](https://mlsanity.com/paper/2605.13034/) (2026)
- [CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine](https://mlsanity.com/paper/2509.26461/) (2025)
- [Story2Proposal: A Scaffold for Structured Scientific Paper Writing](https://mlsanity.com/paper/2603.27065/) (2026)
- [Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports](https://mlsanity.com/paper/2608.14446/) (2026)
- [Scaling Long-Form Story Generation via Narrative State Tracking](https://mlsanity.com/paper/2609.35759/) (2026)
- [Incremental Open-Ended Deep Research with Structured Harness](https://mlsanity.com/paper/2610.11566/) (2026)
- [JevGPT: Thinking Fast and Slow in Autonomous Research](https://mlsanity.com/paper/2610.18272/) (2026)

## Abstract (arXiv)

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.