Large Language Models as Narrative Planning Search Guides
- 29 October 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (2) , 419-428
Abstract
Symbolic planning algorithms and large language models have different strengths and weaknesses for story generation, suggesting hybrid models might leverage advantages from both. Others have proposed using a language model in combination with a partial order planning style algorithm to avoid the need for a hand-written symbolic domain of actions, or generating these domains from natural language input. This paper offers a complementary approach. We propose to use a state space planning algorithm to plan coherent multi-agent stories using hand-written symbolic domains, but with a language model acting as a guide to estimate which events are worth exploring first. We present an initial evaluation of this approach on a set of benchmark narrative planning problems.Keywords
Funding Information
- U.S. Department of War
- National Science Foundation
This publication has 21 references indexed in Scilit:
- Magic3D: High-Resolution Text-to-3D Content Creation2023
- Multiagent Narrative Experience Management as Story Graph PruningIEEE Transactions on Games, 2022
- Solution Density and Search Strategy in Narrative GenerationIEEE Transactions on Games, 2022
- Social Story Worlds With Comme il FautIEEE Transactions on Computational Intelligence and AI in Games, 2014
- Versu—A Simulationist Storytelling SystemIEEE Transactions on Computational Intelligence and AI in Games, 2013
- Character-based interactive storytellingIEEE Intelligent Systems, 2002
- Planning as heuristic searchArtificial Intelligence, 2001
- Story-telling as planning and learningPoetics, 1985
- Causal relatedness and importance of story eventsJournal of Memory and Language, 1985
- Strips: A new approach to the application of theorem proving to problem solvingArtificial Intelligence, 1971