More Like this

1. The Sabre Narrative Planner: Multi-Agent Coordination with Intentions and Beliefs

   Ware, Stephen G.; Siler, Cory (May 2021, AAMAS Conference proceedings)

   Endriss, U.; Nowé, A.; Dignum, F.; Lomuscio, A. (Ed.)

   Sabre is a narrative planner—a centralized, omniscient decision maker that solves a multi-agent storytelling problem. The planner has an author goal it must achieve, but every action taken by an agent must make sense according to that agent’s individual intentions and limited, possibly wrong beliefs. This paper describes the implementation of Sabre, which supports a rich action syntax and imposes no arbitrary limit on the depth of theory of mind. We present a search procedure for generating plans that achieve the author goals while ensuring all agent actions are explained, and we report the system’s performance on several narrative planning benchmark problems. 

   more » « less
2. Sabre: A Narrative Planner Supporting Intention and Deep Theory of Mind

   Ware, Stephen G.; Siler, Cory (October 2021, Proceedings)

   Thue, David; Ware, Stephen G. (Ed.)

   Sabre is a narrative planner—a centralized, omniscient decision maker that solves a multi-agent storytelling problem. The planner has an author goal it must achieve, but every action taken by an agent must make sense according to that agent’s individual intentions and limited, possibly wrong beliefs. This paper describes the implementation of Sabre, which supports a rich action syntax and imposes no arbitrary limit on the depth of theory of mind. We present a search procedure for generating plans that achieve the author goals while ensuring all agent actions are explained, and we report the system’s performance on several narrative planning benchmark problems. 

   more » « less
3. Causal Necessity as a Narrative Planning Step Cost Function

   https://doi.org/10.1609/aiide.v19i1.27511  

   Ware, Stephen G; Senanayake, Lasantha; Farrell, Rachelyn (October 2023, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment)

   Narrative planning generates a sequence of actions which must achieve the author's goal for the story and must be composed only of actions that make sense for the characters who take them. A causally necessary action is one that would make the plan impossible to execute if it were left out. We hypothesize that action sequences which are solutions to narrative planning problems are more likely to feature causally necessary actions than those which are not solutions. In this paper, we show that prioritizing sequences with more causally necessary actions can lead to solutions faster in ten benchmark story planning problems. 

   more » « less
4. Combining Intentionality and Belief: Revisiting Believable Character Plans

   Shirvani, Alireza; Farrell, Rachelyn; Ware, Stephen G. (October 2018, Proceedings of the 14th AAAI International Conference on Artificial Intelligence and Interactive Digital Entertainment)

   In this paper we present two studies supporting a plan-based model of narrative generation that reasons about both intentionality and belief. First we compare the believability of agent plans taken from the spaces of valid classical plans, intentional plans, and belief plans. We show that the plans that make the most sense to humans are those in the overlapping regions of the intentionality and belief spaces. Second, we validate the model’s approach to representing anticipation, where characters form plans that involve actions they expect other characters to take. Using a short interactive scenario we demonstrate that players not only find it believable when NPCs anticipate their actions, but sometimes actively anticipate the actions of NPCs in a way that is consistent with the model. 

   more » « less
5. Language Models as Narrative Planning Heuristics

   https://doi.org/10.1145/3723498.3723815  

   Senanayake, Lasantha; Ware, Stephen G (April 2025, ACM)

   Narrative planning is the process of generating sequences of actions that form coherent and goal-oriented narratives. Classical implementations of narrative planning rely on heuristic search techniques to offer structured story generation but face challenges with scalability due to large branching factors and deep search requirements. Large Language Models (LLMs), with their extensive training on diverse linguistic datasets, excel in understanding and generating coherent narratives. However, their planning ability lacks the precision and structure needed for effective narrative planning. This paper explores a hybrid approach that uses LLMs as heuristic guides within classical search frameworks for narrative planning. We compare various prompt designs to generate LLM heuristic predictions and evaluate their performance against h+, hmax, and relaxed plan heuristics. Additionally, we analyze the ability of relaxed plans to predict the next action correctly, comparing it to the LLMs’ ability to make the same prediction. Our findings indicate that LLMs rarely exceed the accuracy of classical planning heuristics. 

   more » « less