Long-Form Document Generation

Overview

Long-form document generation aims to produce extended texts—such as fiction, scientific papers, financial reports, and medical or legal documents—that remain coherent and meet factual and structural requirements. Common approaches combine hierarchical outlines or narrative-state tracking with retrieval, multi-agent drafting, verification, and iterative revision; training and decoding methods also target length control and reliability. Evaluation spans story and report benchmarks, measuring qualities such as coherence, factual grounding, completeness, and rubric-based quality. A central challenge is balancing global consistency and factuality with fluent local writing, while keeping generation efficient and judging quality reliably across different document types.

Latest papers

CardsList

32 papers2 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

  1. Scaling Long-Form Story Generation via Narrative State Tracking

    Sep 28, 2026Zhennan Wan, Jianfei ChenLong-Form Document GenerationLLM Agents

  2. LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting

    Sep 25, 2026Jiaqi Zhu, Naili Xing, Hexiang Pan +4Long-Form Document GenerationText Generation

  3. MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing

    Sep 14, 2026Jianxiang Ma, Xiaocui Yang, Daling Wang +5Long-Form Document GenerationText Generation

  4. AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation

    Sep 1, 2026Yajing Yang, Yunshan Ma, Kelvin J. L. Koa +1Long-Form Document GenerationEvidence-Grounded Generation

  5. Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training

    Aug 26, 2026Qiankai Xu, Qiguang Chen, Zixin Su +4Long-Form Document GenerationSynthetic Benchmark Generation

  6. Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs

    Aug 23, 2026Yikai Zhao, Qiyan Zhao, Jiaquan Zhang +3Diffusion Language Model DecodingLong-Form Document Generation

  7. MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation

    Aug 21, 2026Ziwu Liu, Guozhong Li, Chen Qiu +2Memory-Augmented Language ModelsLong-Form Document Generation

  8. Novels generated by language models show compressed formal variation

    Aug 12, 2026Mehdy Sedaghat Payam, Justin QuinnLLM EvaluationLong-Form Document Generation

  9. FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation

    Aug 5, 2026Yinghao Tang, Tan Zhenwei, Yiyao Wang +4Financial ServicesLLM Evaluation

  10. RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings

    Aug 2, 2026Raj Shekhar SinghRetrieval-Augmented GenerationLong-Form Document Generation

  11. GEIS: A Generation-Evaluation-Improvement Loop of Agent Skills for Long-Form Article Generation

    Jul 13, 2026Jiale Zhang, Juntao Hu, Zhijian OuLong-Form Document GenerationLLM Agent Self-Improvement

  12. Prompt-to-Paper: Agentic AI System for Bioinformatics

    Jul 5, 2026Ramsha Kamran, Maheera Amjad, Zartasha Mustansar +3Long-Form Document GenerationAI-Assisted Scientific Research

  13. Not All Claims Are Equally Risky: FACTOR for Adaptive Verification in Factual Long-Form Generation

    Jun 21, 2026Areeba Hassan, Arooj Kausar, Syeda Kisaa Fatima +2LLM Answer VerificationLong-Form Document Generation

  14. ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research

    Jun 18, 2026Zhibang Yang, Xinke Jiang, Yuzhen Xiao +9Long-Form Document GenerationDeep Research Agents

  15. IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking

    Jun 8, 2026Zechen Sun, Yuyang Sun, Zecheng Tang +6Open-Ended GenerationLong-Form Document Generation

  16. Building Reliable Long-Form Generation via Hallucination Rejection Sampling

    Jun 2, 2026Lin Li, Georgia Channing, Suhaas M Bhat +2Long-Form Document GenerationLLM Hallucination Mitigation

  17. Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation

    May 26, 2026Ning Wu, Rui Liu, Xinkun Lin +5Medical Report GenerationLong-Form Document Generation

  18. Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation

    May 26, 2026Zixuan Yang, Yiqun Chen, Wei Yang +7Open-Ended GenerationReward Modeling

  19. Towards Human-Level Book-Writing Capability

    May 16, 2026Jan Zierstek, Matteo Batelic, Maya Medjad +1Long-Form Document GenerationLLM Fine-Tuning

  20. Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality

    May 3, 2026Wen Luo, Guangyue Peng, Liang Wang +7Long-Form Document GenerationLLM Hallucination Mitigation

  21. On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility

    May 2, 2026Zhitao He, Haolin Yang, Rui Min +2LLM EvaluationLong-Form Document Generation

  22. When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis

    Apr 17, 2026Justice Owusu Agyemang, Michael Agyare, Miriam Kobbinah +2LLM Inference EfficiencyLong-Form Document Generation

  23. Improving Attributed Long-form Question Answering with Intent Awareness

    Mar 28, 2026Xinran Zhao, Aakanksha Naik, Jay DeYoung +4Long-Form Document GenerationText Generation

  24. BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation

    Mar 15, 2026Zhaoyi Li, Xu Zhang, Xiaojun WanNarrative GenerationText Generation