Dual-Frontier: When Can an Agent Trust Its World Model?· 双重前沿：智能体何时信任其世界模型？
Learned world models are becoming essential to general-purpose agents: by predicting action consequences, they support planning and decision-making while reducing reliance on costly trial and error. This reliance creates a fundamental ambiguity: when a world-model-guided decision fails, the trajectory alone may not reveal whether the agent's decision rule or the world model caused the loss. We formalize this failure-attribution problem as a counterfactual decomposition of return loss and prove that its components are not identifiable from passive interaction, even for finite-horizon planners. This obstruction motivates Dual-Frontier, a learning principle that admits a world-model-guided decision only when its predicted advantage exceeds a certified bound on decision-relevant world-model er
探讨智能体何时能信任其世界模型及其决策的可靠度。
- 核心方法
- 提出Dual-Frontier学习原则，确保世界模型指导的决策优势超过与决策相关的世界模型误差认证界限时才被采纳。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 当以世界模型指导的决策失败时，很难确定是决策规则还是世界模型本身的问题。
- 关键实验
- 未提供
- 主要贡献
- 解决了世界模型失败归因问题，提高了智能体决策的可信度和安全性。
- 意义与局限
- 对于提高智能体在复杂环境中的适应能力和决策质量具有重要意义，但仅基于被动交互无法完全解决问题。