# Interactive AI with a Theory of Mind

arXiv: https://arxiv.org/abs/1912.05284 · HTML: https://mlsanity.com/paper/1912.05284/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Generative AI](https://mlsanity.com/paper/2309.07930/) (2023)
- [From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape](https://mlsanity.com/paper/2312.10868/) (2023)
- [Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy](https://mlsanity.com/paper/2210.09435/) (2022)
- [Differentiable User Models](https://mlsanity.com/paper/2211.16277/) (2022)
- [Position Paper on Dataset Engineering to Accelerate Science](https://mlsanity.com/paper/2303.05545/) (2023)
- [What should I say? -- Interacting with AI and Natural Language Interfaces](https://mlsanity.com/paper/2401.06382/) (2024)
- [Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?](https://mlsanity.com/paper/2509.10875/) (2025)

## Abstract (arXiv)

Understanding each other is the key to success in collaboration. For humans, attributing mental states to others, the theory of mind, provides the crucial advantage. We argue for formulating human--AI interaction as a multi-agent problem, endowing AI with a computational theory of mind to understand and anticipate the user. To differentiate the approach from previous work, we introduce a categorisation of user modelling approaches based on the level of agency learnt in the interaction. We describe our recent work in using nested multi-agent modelling to formulate user models for multi-armed bandit based interactive AI systems, including a proof-of-concept user study.