ACL Findings2025
A Cognitive Writing Perspective for Constrained Long-Form Text Generation
Kaiyang Wan, Honglin Mu, Rui Hao, Haoran Luo, Tianle Gu, Xiuying Chen
Abstract
Like humans, Large Language Models (LLMs) struggle to generate high-quality long-form text that adheres to strict requirements in a single pass. This challenge is unsurprising, as successful human writing, according to the Cognitive Writing Theory, is a complex cognitive process involving iterative planning, translating, reviewing, and monitoring. Motivated by these cognitive principles, we aim to equip LLMs with human-like cognitive writing capabilities through CogWriter, a novel training-free framework that transforms LLM constrained longform text generation into a systematic cognitive writing paradigm. Our framework consists of two key modules: (1) a Planning Agent that performs hierarchical planning to decompose the task, and (2) multiple Generation Agents that execute these plans in parallel. The system maintains quality via continuous monitoring and reviewing mechanisms, which evaluate outputs against specified requirements and trigger necessary revisions. CogWriter demonstrates exceptional performance on LongGenBench, a benchmark for complex constrained longform text generation. Even when using Qwen-2.5-14B as its backbone, CogWriter surpasses GPT-4o by 22% in complex instruction completion accuracy while reliably generating texts exceeding 10,000 words. We hope this cognitive science-inspired approach provides a paradigm for LLM writing advancements: CogWriter.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
7 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Self-Refine: Iterative Refinement with Self-Feedback cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA cites Self-Refine: Iterative Refinement with Self-Feedback
- A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Cited by top-tier papers7
- WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep ResearchZijian Li, Xin Guan, Bo Zhang, Shen Huang et al.ICLR 2026 · 48 citations
- A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QAKaiyang Wan, Lang Gao, Honglin Mu, Preslav Nakov et al.ICLR 2026 · 10 citations
- StoryAlign: Evaluating and Training Reward Models for Story GenerationHaotian Xia, Hao Peng, Yunjia Qi, Bin Xu et al.ICLR 2026 · 2 citations
- DeepWriter: A Multi-Agent Collaboration Framework for Information-rich Ultra-long Book WritingMing Wang, Minghao Hu, Xiuli Kang, Li He et al.AAAI 2026
- Tractable Transformers for Flexible Conditional GenerationAnji Liu, Xuejie Liu, Dayuan Zhao, Mathias Niepert et al.ICML 2025
Builds on24
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
- Lift Yourself Up: Retrieval-augmented Text Generation with Self-MemoryXin Cheng, Di Luo, Xiuying Chen, Lemao Liu et al.NeurIPS 2023 · 177 citations
- AutoSurvey: Large Language Models Can Automatically Write SurveysYidong Wang, Qi Guo, Wenjin Yao, Hongbo Zhang et al.NeurIPS 2024 · 151 citations
Related papers
- SuperWriter: Reflection-Driven Long-Form Generation with Large Language ModelsYuhao Wu, Yushi Bai, Zhiqiang Hu, Juanzi Li et al.ACL Findings 2026 · 1 citation
- IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural ThinkingZechen Sun, Yuyang Sun, Zecheng Tang, Juntao Li et al.ACL 2026
- LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement LearningYuhao Wu, Yushi Bai, Zhiqiang Hu, Roy Ka-Wei Lee et al.ICLR 2026 · 9 citations
- LongGenBench: Benchmarking Long-Form Generation in Long Context LLMsYuhao Wu, Ming Shan Hee, Zhiqiang Hu, Roy Ka-Wei LeeICLR 2025
- Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement LearningXuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu et al.ACL 2026 · 8 citations
