Metraipolis › archive › dc_a8edb3cb7ef6
Structured Machine Theory of Mind from Agent Trajectories — arXiv:2611.07208
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07208
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:44:08.903Z
- SHA-256 of the archived text
8656fb1f46c610e4c86c707e32cef40ce6fee7ef73e37bd0cbe0261b5384facf- Stable URL of this page
https://metraipolis.com/documento/dc_a8edb3cb7ef6
How to cite
Structured Machine Theory of Mind from Agent Trajectories — arXiv:2611.07208 — arXiv (en), https://arxiv.org/abs/2611.07208 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a8edb3cb7ef6 (Metraipolis archive dc_a8edb3cb7ef6, sha256 8656fb1f46c610e4c86c707e32cef40ce6fee7ef73e37bd0cbe0261b5384facf)
BibTeX
@misc{dca8edb3cb7ef6,
title = {Structured Machine Theory of Mind from Agent Trajectories — arXiv:2611.07208},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07208},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a8edb3cb7ef6; sha256 8656fb1f46c610e4c86c707e32cef40ce6fee7ef73e37bd0cbe0261b5384facf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07208. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predictive models of human behavior trained on large-scale trajectory data optimize for statistical accuracy without representing the mental states that causally generate behavior. Such models support prediction but not principled intervention: they cannot answer how an agent's behavior would change if its beliefs or preferences were different. We introduce Structured Machine Theory of Mind (SMToM), a framework that attributes explicit, independently supervised belief and desire representations from observed trajectories within a Belief-Desire-Intention (BDI) causal structure. The central architectural element is a goal head that consumes only the predicted mental-state channels and a current-trajectory embedding; counterfactual intervention on beliefs and desires is a direct operation. We instantiate SMToM on a controlled pedestrian navigation domain where ground-truth mental states are known by construction, enabling evaluation of attribution accuracy, local channel interventions, and trajectory-level counterfactual diagnostics. The resulting model, BDIBottleneck, improves over trajectory-only and unsupervised-context neural baselines. It is also competitive with a matched auxiliary-supervised context baseline while providing an editable mental-state interface that the unbottlenecked baseline lacks. Counterfactual experiments on desires confirm that substituting an agent's inferred preferences with a different activity type coherently shifts predicted destinations toward relevant locations. Counterfactual experiments on beliefs confirm that marking a location as unavailable in the agent's belief state reduces its predicted probability as a destination, though in a complex way. These results demonstrate, in a controlled navigation setting, that explicit BDI-structured supervision is a viable foundation for interpretable and counterfactual analysis of longitudinal trajectory data. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.07208 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-06T14:21:42.617Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).