Cover Image

AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rosas, Fernando, Boyd, Alexander, Baltieri, Manuel
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Systems and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A "good regulator theorem" for embodied agents
by: Virgo, Nathaniel, et al.
Published: (2025)

From monoliths to modules: Decomposing transducers for efficient world modelling
by: Boyd, Alexander, et al.
Published: (2025)

An agent design with goal reaching guarantees for enhancement of learning
by: Osinenko, Pavel, et al.
Published: (2024)

A phase-aware AI car-following model for electric vehicles with adaptive cruise control: Development and validation using real-world data
by: Liu, Yuhui, et al.
Published: (2025)

Machine Learning for the Internet of Underwater Things: From Fundamentals to Implementation
by: Omeke, Kenechi, et al.
Published: (2026)

Influence of the Geometry of the world model on Curiosity Based Exploration
by: Sergeant-Perthuis, Grégoire, et al.
Published: (2023)

Towards Real-world Deployment of NILM Systems: Challenges and Practices
by: Xue, Junyu, et al.
Published: (2024)

Learning-based Multi-agent Race Strategies in Formula 1
by: Fieni, Giona, et al.
Published: (2026)

Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges
by: Kalian, Alexander D., et al.
Published: (2025)

Facilitating Emergency Vehicle Passage in Congested Urban Areas Using Multi-agent Deep Reinforcement Learning
by: Su, Haoran
Published: (2025)

Reinforcement learning meets bioprocess control through behaviour cloning: Real-world deployment in an industrial photobioreactor
by: Gil, Juan D., et al.
Published: (2025)

Perspectives on a Reliability Monitoring Framework for Agentic AI Systems
by: Flehmig, Niclas, et al.
Published: (2025)

AI Explainability for Power Electronics: From a Lipschitz Continuity Perspective
by: Li, Xinze, et al.
Published: (2025)

Approaches to Analysis and Design of AI-Based Autonomous Vehicles
by: Yan, Tao, et al.
Published: (2025)

Robustness Analysis of AI Models in Critical Energy Systems
by: Dogoulis, Pantelis, et al.
Published: (2024)

Promising and worth-to-try future directions for advancing state-of-the-art surrogates methods of agent-based models in social and health computational sciences
by: Elsheikh, Atiyah
Published: (2024)

AI-Driven Optimization under Uncertainty for Mineral Processing Operations
by: Xu, William, et al.
Published: (2025)

Explainable AI based System for Supply Air Temperature Forecast
by: Eik, Marika, et al.
Published: (2025)

Towards provable probabilistic safety for scalable embodied AI systems
by: He, Linxuan, et al.
Published: (2025)

Human-in-the-Loop AI for HVAC Management Enhancing Comfort and Energy Efficiency
by: Liang, Xinyu, et al.
Published: (2025)

Reliability, Resilience and Human Factors Engineering for Trustworthy AI Systems
by: Mishra, Saurabh, et al.
Published: (2024)

AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation
by: Brown, Colin, et al.
Published: (2026)

A Time-efficient Prioritised Scheduling Algorithm to Optimise Initial Flock Formation of Drones
by: Warnakulasooriya, Sujan, et al.
Published: (2025)

Control of Renewable Energy Communities using AI and Real-World Data
by: Fonseca, Tiago, et al.
Published: (2025)

The Distribution Shift Problem in Transportation Networks using Reinforcement Learning and AI
by: Taschin, Federico, et al.
Published: (2025)

From Failure Modes to Reliability Awareness in Generative and Agentic AI System
by: Janet, et al.
Published: (2025)

humancompatible.interconnect: Testing Properties of Repeated Uses of Interconnections of AI Systems
by: Nazarov, Rodion, et al.
Published: (2025)

Decoding the Black Box: Integrating Moral Imagination with Technical AI Governance
by: Tallam, Krti
Published: (2025)

Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey
by: Chen, Xiaojing, et al.
Published: (2026)

Automotive Engineering-Centric Agentic AI Workflow Framework
by: Son, Tong Duy, et al.
Published: (2026)

Control Analysis and Design for Autonomous Vehicles Subject to Imperfect AI-Based Perception
by: Yan, Tao, et al.
Published: (2025)

Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery
by: Yang, Zhenning, et al.
Published: (2026)

PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses
by: Badmus, Emmanuel O., et al.
Published: (2025)

Enhancing AI System Resiliency: Formulation and Guarantee for LSTM Resilience Based on Control Theory
by: Yoshihara, Sota, et al.
Published: (2025)

X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysis
by: Yihan, et al.
Published: (2025)

AI- and Ontology-Based Enhancements to FMEA for Advanced Systems Engineering: Current Developments and Future Directions
by: Younus, Haytham, et al.
Published: (2025)

Bridging Qualitative Rubrics and AI: A Binary Question Framework for Criterion-Referenced Grading in Engineering
by: Chen, Lili, et al.
Published: (2026)

Conversational Demand Response: Bidirectional Aggregator-Prosumer Coordination through Agentic AI
by: Makroum, Reda El, et al.
Published: (2026)

Customized User Plane Processing via Code Generating AI Agents for Next Generation Mobile Networks
by: Ma, Xiaowen, et al.
Published: (2026)

Physically Analyzable AI-Based Nonlinear Platoon Dynamics Modeling During Traffic Oscillation: A Koopman Approach
by: Tian, Kexin, et al.
Published: (2024)