# An Active Inference Model of Mouse Point-and-Click Behaviour

arXiv: https://arxiv.org/abs/2510.14611 · HTML: https://mlsanity.com/paper/2510.14611/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Sophisticated Inference](https://mlsanity.com/paper/2006.04120/) (2020)
- [Active Inference and Human--Computer Interaction](https://mlsanity.com/paper/2412.14741/) (2024)
- [Active inference, eye movements and oculomotor delays](https://mlsanity.com/paper/1610.05564/) (2016)
- [Optimal Feedback Control for Modeling Human-Computer Interaction](https://mlsanity.com/paper/2110.00443/) (2021)
- [Simulating Interaction Movements via Model Predictive Control](https://mlsanity.com/paper/2204.09115/) (2022)
- [Intermittent control as a model of mouse movements](https://mlsanity.com/paper/2103.08558/) (2021)
- [Interactive Inference: A Neuromorphic Theory of Human-Computer Interaction](https://mlsanity.com/paper/2502.05935/) (2025)

## Abstract (arXiv)

We explore the use of Active Inference (AIF) as a computational user model for spatial pointing, a key problem in Human-Computer Interaction (HCI). We present an AIF agent with continuous state, action, and observation spaces, performing one-dimensional mouse pointing and clicking. We use a simple underlying dynamic system to model the mouse cursor dynamics with realistic perceptual delay. In contrast to previous optimal feedback control-based models, the agent's actions are selected by minimizing Expected Free Energy, solely based on preference distributions over percepts, such as observing clicking a button correctly. Our results show that the agent creates plausible pointing movements and clicks when the cursor is over the target, with similar end-point variance to human users. In contrast to other models of pointing, we incorporate fully probabilistic, predictive delay compensation into the agent. The agent shows distinct behaviour for differing target difficulties without the need to retune system parameters, as done in other approaches. We discuss the simulation results and emphasize the challenges in identifying the correct configuration of an AIF agent interacting with continuous systems.