剖析世界模型安全挑战，推动可信AI代理发展
World Models: The Safety Perspective
- 从可信性视角系统分析当前世界模型技术
- 指出其在关键应用中面临的安全风险与局限
- 面向研究人员呼吁共建更安全的世界模型体系
随着大语言模型的普及，世界模型（World Models, WM）在人工智能研究领域，特别是在AI代理系统中受到广泛关注，正逐步成为构建智能体系统的重要基础。世界模型旨在帮助智能体预测环境状态的未来演变或填补缺失信息，从而实现有效规划与安全行为。其安全性在关键应用场景中至关重要。本文基于全面调研，从可信性与安全性的角度，深入分析当前最先进的世界模型技术及其影响，揭示关键技术挑战及其潜在影响，旨在呼吁研究社区协作提升世界模型的安全性与可信度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。