---
title: "Mental Models of AI Agents in a Cooperative Game Setting (Extended Abstract)"
authors:
  - "Katy Ilonka Gero"
  - "Zahra Ashktorab"
  - "Casey Dugan"
  - "Qian Pan"
  - "James Johnson"
  - "Werner Geyer"
  - "Maria Ruiz"
  - "Sarah Miller"
  - "David R. Millen"
  - "Murray Campbell"
  - "Sadhana Kumaravel"
  - "Wei Zhang"
doi: "10.24963/ijcai.2021/648"
url: "https://ijcai.org/proceedings/2021/648"
pdf: "https://ijcai.org/proceedings/2021/0648.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "4770-4774"
track: "Sister Conferences Best Papers"
keywords:
  - "Humans and AI: Cognitive Modeling"
  - "Humans and AI: Human-Computer Interaction"
  - "Humans and AI: Human-AI Collaboration"
  - "Heuristic Search and Game Playing: Game Playing"
---

# Mental Models of AI Agents in a Cooperative Game Setting (Extended Abstract)

Katy Ilonka Gero, Zahra Ashktorab, Casey Dugan, Qian Pan, James Johnson, Werner Geyer, Maria Ruiz, Sarah Miller, David R. Millen, Murray Campbell, Sadhana Kumaravel, Wei Zhang

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 4770-4774. DOI: [10.24963/ijcai.2021/648](https://doi.org/10.24963/ijcai.2021/648)

## Abstract

As more and more forms of AI become prevalent, it becomes increasingly important to understand how people develop mental models of these systems. In this work we study people's mental models of an AI agent in a cooperative word guessing game. We run a study in which people play the game with an AI agent while ``thinking out loud''; through thematic analysis we identify features of the mental models developed by participants. In a large-scale study we have participants play the game with the AI agent online and use a post-game survey to probe their mental model. We find that those who win more often have better estimates of the AI agent's abilities. We present three components---global knowledge, local knowledge, and knowledge distribution---for modeling AI systems and propose that understanding the underlying technology is insufficient for developing appropriate conceptual models---analysis of behavior is also necessary.