Saved in:
Bibliographic Details
Main Authors: Doering, Nigel, Malladi, Rahath, Sangwan, Arshia, Danks, David, Rahman, Tauhidur
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.16826
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908840400781312
author Doering, Nigel
Malladi, Rahath
Sangwan, Arshia
Danks, David
Rahman, Tauhidur
author_facet Doering, Nigel
Malladi, Rahath
Sangwan, Arshia
Danks, David
Rahman, Tauhidur
contents Theory of mind (ToM) enables AI systems to infer agents' hidden goals and mental states, but existing approaches focus mainly on small human understandable gridworld spaces. We introduce HiVAE, a hierarchical variational architecture that scales ToM reasoning to realistic spatiotemporal domains. Inspired by the belief-desire-intention structure of human cognition, our three-level VAE hierarchy achieves substantial performance improvements on a 3,185-node campus navigation task. However, we identify a critical limitation: while our hierarchical structure improves prediction, learned latent representations lack explicit grounding to actual mental states. We propose self-supervised alignment strategies and present this work to solicit community feedback on grounding approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16826
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HiVAE: Hierarchical Latent Variables for Scalable Theory of Mind
Doering, Nigel
Malladi, Rahath
Sangwan, Arshia
Danks, David
Rahman, Tauhidur
Machine Learning
Artificial Intelligence
Theory of mind (ToM) enables AI systems to infer agents' hidden goals and mental states, but existing approaches focus mainly on small human understandable gridworld spaces. We introduce HiVAE, a hierarchical variational architecture that scales ToM reasoning to realistic spatiotemporal domains. Inspired by the belief-desire-intention structure of human cognition, our three-level VAE hierarchy achieves substantial performance improvements on a 3,185-node campus navigation task. However, we identify a critical limitation: while our hierarchical structure improves prediction, learned latent representations lack explicit grounding to actual mental states. We propose self-supervised alignment strategies and present this work to solicit community feedback on grounding approaches.
title HiVAE: Hierarchical Latent Variables for Scalable Theory of Mind
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.16826