# Memory-Augmented Theory of Mind Network

arXiv: https://arxiv.org/abs/2301.06926 · HTML: https://mlsanity.com/paper/2301.06926/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 17 Jan 2023.

## Builds on (most cited first, 6 of 6)

- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Evaluating Theory of Mind in Question Answering](https://mlsanity.com/paper/1808.09352/) (2018)
- [Learning to Remember Rare Events](https://mlsanity.com/paper/1703.03129/) (2017)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others](https://mlsanity.com/paper/2102.11938/) (2021)
- [Model-Based Episodic Memory Induces Dynamic Hybrid Controls](https://mlsanity.com/paper/2111.02104/) (2021)

## Built on by (most cited first, 6 of 6)

- [OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2402.06044/) (2024)
- [Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions](https://mlsanity.com/paper/2407.06762/) (2024)
- [Remembering What Is Important: A Factorised Multi-Head Retrieval and Auxiliary Memory Stabilisation Scheme for Human Motion Prediction](https://mlsanity.com/paper/2305.11394/) (2023)
- [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026)
- [Memorizing Documents with Guidance in Large Language Models](https://mlsanity.com/paper/2406.15996/) (2024)
- [Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling](https://mlsanity.com/paper/2605.12411/) (2026)

## Abstract (arXiv)

Social reasoning necessitates the capacity of theory of mind (ToM), the ability to contextualise and attribute mental states to others without having access to their internal cognitive structure. Recent machine learning approaches to ToM have demonstrated that we can train the observer to read the past and present behaviours of other agents and infer their beliefs (including false beliefs about things that no longer exist), goals, intentions and future actions. The challenges arise when the behavioural space is complex, demanding skilful space navigation for rapidly changing contexts for an extended period. We tackle the challenges by equipping the observer with novel neural memory mechanisms to encode, and hierarchical attention to selectively retrieve information about others. The memories allow rapid, selective querying of distal related past behaviours of others to deliberatively reason about their current mental state, beliefs and future behaviours. This results in ToMMY, a theory of mind model that learns to reason while making little assumptions about the underlying mental processes. We also construct a new suite of experiments to demonstrate that memories facilitate the learning process and achieve better theory of mind performance, especially for high-demand false-belief tasks that require inferring through multiple steps of changes.