From Particles to Agents: Hallucination as a Metric for Cognitive Friction in Spatial Simulation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sánchez-Vaquerizo, Javier Argota, Monsivais, Luis Borunda
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910004953481216
author Sánchez-Vaquerizo, Javier Argota
Monsivais, Luis Borunda
author_facet Sánchez-Vaquerizo, Javier Argota
Monsivais, Luis Borunda
contents Traditional architectural simulations (e.g. Computational Fluid Dynamics, evacuation, structural analysis) model elements as deterministic physics-based "particles" rather than cognitive "agents". To bridge this, we introduce \textbf{Agentic Environmental Simulations}, where Large Multimodal generative models actively predict the next state of spatial environments based on semantic expectation. Drawing on examples from accessibility-oriented AR pipelines and multimodal digital twins, we propose a shift from chronological time-steps to Episodic Spatial Reasoning, where simulations advance through meaningful, surprisal-triggered events. Within this framework we posit AI hallucinations as diagnostic tools. By formalizing the \textbf{Cognitive Friction} ($C_f$) it is possible to reveal "Phantom Affordances", i.e. semiotic ambiguities in built space. Finally, we challenge current HCI paradigms by treating environments as dynamic cognitive partners and propose a human-centered framework of cognitive orchestration for designing AI-driven simulations that preserve autonomy, affective clarity, and cognitive integrity.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21977
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Particles to Agents: Hallucination as a Metric for Cognitive Friction in Spatial Simulation
Sánchez-Vaquerizo, Javier Argota
Monsivais, Luis Borunda
Human-Computer Interaction
Artificial Intelligence
Computers and Society
Primary 68U20, Secondary 68T45, 68T37, 68U07, 68T05
H.5.2; I.2.10; I.2.11; I.6.8; J.5; K.4.1
Traditional architectural simulations (e.g. Computational Fluid Dynamics, evacuation, structural analysis) model elements as deterministic physics-based "particles" rather than cognitive "agents". To bridge this, we introduce \textbf{Agentic Environmental Simulations}, where Large Multimodal generative models actively predict the next state of spatial environments based on semantic expectation. Drawing on examples from accessibility-oriented AR pipelines and multimodal digital twins, we propose a shift from chronological time-steps to Episodic Spatial Reasoning, where simulations advance through meaningful, surprisal-triggered events. Within this framework we posit AI hallucinations as diagnostic tools. By formalizing the \textbf{Cognitive Friction} ($C_f$) it is possible to reveal "Phantom Affordances", i.e. semiotic ambiguities in built space. Finally, we challenge current HCI paradigms by treating environments as dynamic cognitive partners and propose a human-centered framework of cognitive orchestration for designing AI-driven simulations that preserve autonomy, affective clarity, and cognitive integrity.
title From Particles to Agents: Hallucination as a Metric for Cognitive Friction in Spatial Simulation
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
Primary 68U20, Secondary 68T45, 68T37, 68U07, 68T05
H.5.2; I.2.10; I.2.11; I.6.8; J.5; K.4.1
url https://arxiv.org/abs/2601.21977