# SWAG: Storytelling With Action Guidance

arXiv: https://arxiv.org/abs/2402.03483 · HTML: https://mlsanity.com/paper/2402.03483/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking](https://mlsanity.com/paper/2004.14967/) (2020)
- [Controllable Neural Story Plot Generation via Reward Shaping](https://mlsanity.com/paper/1809.10736/) (2018)
- [Learning to Generate Better Than Your LLM](https://mlsanity.com/paper/2306.11816/) (2023)
- [Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation](https://mlsanity.com/paper/1904.02357/) (2019)
- [A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation](https://mlsanity.com/paper/1808.06945/) (2018)
- [Wordcraft: a Human-AI Collaborative Editor for Story Writing](https://mlsanity.com/paper/2107.07430/) (2021)
- [Controllable Generation from Pre-trained Language Models via Inverse Prompting](https://mlsanity.com/paper/2103.10685/) (2021)
- [Automatic Story Generation: Challenges and Attempts](https://mlsanity.com/paper/2102.12634/) (2021)
- [Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes](https://mlsanity.com/paper/2104.04039/) (2021)
- [Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning](https://mlsanity.com/paper/2112.08593/) (2021)
- [Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning](https://mlsanity.com/paper/2210.07792/) (2022)
- [End-to-end Story Plot Generator](https://mlsanity.com/paper/2310.08796/) (2023)
- [A Temporal Variational Model for Story Generation](https://mlsanity.com/paper/2109.06807/) (2021)

## Built on by (most cited first, 8 of 8)

- [Preference Optimization with Multi-Sample Comparisons](https://mlsanity.com/paper/2410.12138/) (2024)
- [Scaling Properties of Diffusion Models for Perceptual Tasks](https://mlsanity.com/paper/2411.08034/) (2024)
- [Assessing Language Models' Worldview for Fiction Generation](https://mlsanity.com/paper/2408.07904/) (2024)
- [Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models](https://mlsanity.com/paper/2608.19893/) (2026)
- [WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Models](https://mlsanity.com/paper/2412.10582/) (2024)
- [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026)
- [POLARIS: Guiding Small Models to Write Long Stories](https://mlsanity.com/paper/2606.04095/) (2026)
- [Scaling Long-Form Story Generation via Narrative State Tracking](https://mlsanity.com/paper/2609.35759/) (2026)

## Abstract (arXiv)

Automated long-form story generation typically employs long-context large language models (LLMs) for one-shot creation, which can produce cohesive but not necessarily engaging content. We introduce Storytelling With Action Guidance (SWAG), a novel approach to storytelling with LLMs. Our approach frames story writing as a search problem through a two-model feedback loop: one LLM generates story content, and another auxiliary LLM is used to choose the next best "action" to steer the story's future direction. Our results show that SWAG can substantially outperform previous end-to-end story generation techniques when evaluated by GPT-4 and through human evaluation. Our SWAG pipeline using only small open-source models surpasses GPT-3.5-Turbo.