Research map / Large language models / Agents, code and math
Plan-and-Write: Towards Better Automatic Storytelling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add dynamic storyline planning while writing | Inc-S2S · ROCStories test | human fidelity preference: 12.9 -> 35.8 | Helped |
| Add full storyline planning before writing | Cond-LM · ROCStories test | human coherence preference: 32.3 -> 39.4 | Helped |
| Plan the full storyline before writing instead of planning dynamically | Plan-and-Write · ROCStories test | human coherence preference: 28.27 vs 49.47 | Helped |
| Plan a storyline before generating the story | Non-planning story generation baselines · ROCStories test | inter-story repetition | Helped |
| Plan a storyline before generating the story | Non-planning story generation baselines · ROCStories test | intra-story repetition | Helped |
| Use dynamic planning, which interleaves planning and writing | Plan-and-Write · ROCStories test | intra-story repetition in final sentences | Hurt |
| Plan the complete storyline before writing | Plan-and-Write · ROCStories test | storyline BLEU-1: 6.46 -> 9.53 | Helped |
| Remove storyline repetition optimization that forbids repeated words (ablation) | Dynamic · ROCStories test | BLEU-1: 28.47 -> 26.16 | Hurt |
| Remove storyline repetition optimization that forbids repeated words (ablation) | Dynamic · ROCStories test | BLEU-2: 11.49 -> 10.39 | No clear effect |
| Remove storyline repetition optimization that forbids repeated words (ablation) | Static · ROCStories test | BLEU-4: 3.44 -> 3.27 | Hurt |
Closest papers by meaning
- Agents' Room: Narrative Generation through Multi-step Collaboration (ICLR 2025 · similarity 0.88)
- Does Robin Hood Use a Lightsaber?: Automated Planning for Storytelling (AAAI 2024 · similarity 0.86)
- StoryBox: Collaborative Multi-Agent Simulation for Hybrid Bottom-Up Long-Form Story Generation Using Large Language Models (AAAI 2026 · similarity 0.86)
- NaRuto: Automatically Acquiring Planning Models from Narrative Texts (AAAI 2024 · similarity 0.85)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.84)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.