mlsanityData to 14 Oct 2026

World Models: The Safety Perspective

arXiv 2411.07690 ↗First posted 12 Nov 2024cs.AIcited by 9

On the map: World models → World models for language agents

Abstract (arXiv)

With the proliferation of the Large Language Model (LLM), the concept of World Models (WM) has recently attracted a great deal of attention in the AI research community, especially in the context of AI agents. It is arguably evolving into an essential foundation for building AI agent systems. A WM is intended to help the agent predict the future evolution of environmental states or help the agent fill in missing information so that it can plan its actions and behave safely. The safety property of WM plays a key role in their effective use in critical applications. In this work, we review and analyze the impacts of the current state-of-the-art in WM technology from the point of view of trustworthiness and safety based on a comprehensive survey and the fields of application envisaged. We provide an in-depth analysis of state-of-the-art WMs and derive technical research challenges and their impact in order to call on the research community to collaborate on improving the safety and trustworthiness of WM.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 64 of its 77 references that are in the map. First posted on arXiv 12 Nov 2024.

Builds on

64 of 77 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought22 Jun

Other references · 63

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2016Improved Techniques for Training GANscited by 2,970
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  5. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  7. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  10. 2023Mastering Diverse Domains through World Modelscited by 1,253
  11. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  12. 2020Mastering Atari with Discrete World Modelscited by 1,007
38 more
  1. 2018DeepMind Control Suitecited by 956
  2. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  3. 2022A Generalist Agentcited by 808
  4. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
  5. 2024Genie: Generative Interactive Environmentscited by 747
  6. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 637
  7. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 590
  8. 2024Revisiting Feature Prediction for Learning Visual Representations from Videocited by 531
  9. 2024Large Language Models: A Surveycited by 525
  10. 2019Model-Based Reinforcement Learning for Ataricited by 502
  11. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 490
  12. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 477
  13. 2023Learning Interactive Real-World Simulatorscited by 458
  14. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  15. 2022DayDreamer: World Models for Physical Robot Learningcited by 400
  16. 2022MAGVIT: Masked Generative Video Transformercited by 346
  17. 2022Transformers are Sample-Efficient World Modelscited by 328
  18. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 319
  19. 2015Deep multi-scale video prediction beyond mean square errorcited by 300
  20. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 261
  21. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  22. 2023Multimodal Large Language Models: A Surveycited by 195
  23. 2024DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generationcited by 191
  24. 2022Guided Conditional Diffusion for Controllable Traffic Simulationcited by 190
  25. 2023Panacea: Panoramic and Controllable Video Generation for Autonomous Drivingcited by 168
  26. 2023MotionLM: Multi-Agent Motion Forecasting as Language Modelingcited by 156
  27. 2022Model-Based Imitation Learning for Urban Drivingcited by 150
  28. 2022Diffusion Models for Video Prediction and Infillingcited by 135
  29. 2023Vision Language Models in Autonomous Driving: A Survey and Outlookcited by 126
  30. 2023Language-Guided Traffic Simulation via Scene-Level Diffusioncited by 111
  31. 2022TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarioscited by 106
  32. 2023Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusioncited by 106
  33. 2023ADriver-I: A General World Model for Autonomous Drivingcited by 104
  34. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  35. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 99
  36. 2023WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generationcited by 93
  37. 2024DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Drivingcited by 93
  38. 2023Language Conditioned Traffic Generationcited by 87

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025The Role of World Models in Shaping Autonomous Driving: A Comprehensive Surveycited by 29
  2. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 14
  3. 2025Linear Spatial World Models Emerge in Large Language Modelscited by 6
  4. 2025The Safety Challenge of World Models for Embodied AI Agents: A Reviewcited by 6
  5. 2025Toward Stable World Models: Measuring and Addressing World Instability in Generative Environmentscited by 5
  6. 2026Medical world models in healthcare: foundations, applications, and challenges for trustworthy clinical translationcited by 4
  7. 2026Safety, Security, and Cognitive Risks in World Modelscited by 3
  8. 2026ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Controlcited by 2
  9. 2026Quo Vadis, World Modeling?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Large Language Model Safety: A Holistic Survey
  2. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
  3. 2024Language-Guided World Models: A Model-Based Approach to AI Control
  4. 2025OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
  5. 2025Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation
  6. 2024Agent-SafetyBench: Evaluating the Safety of LLM Agents
  7. 2024AI Safety in Generative AI Large Language Models: A Survey
  8. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety