什么是有能力的智能体必须知道：在不确定性下鲁棒决策制定的选取定理
What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty
AI总结：
本文探讨了在不确定性下智能体必需的内部结构，证明了强任务表现迫使世界模型、信念记忆及持久变量的必要性，提出了选取定理以解决部分可观测性和任务分布下的决策问题。
摘要：
随着人工智能体能力的提升，什么内部结构是智能体在不确定性下有效行动所必需的？经典结果表明最优控制可以使用信念状态或世界模型实现，但并非必须如此。我们证明了定量的“选取定理”，表明强任务表现（低平均案例遗憾）迫使世界模型、信念状记忆以及在任务混合下持久变量，这些变量类似于与情绪相关的核心原始变量，以及在块结构任务下的信息模块化。我们的结果涵盖了随机策略、部分可观测性和任务分布下的评估，不假设最优性、确定性或对显式模型的访问。技术上，我们将预测建模减少为二进制“投注”决策，并证明遗憾界限限制了对次优投注的概率质量，强制需要预测区分以分离高边际结果。在完全可观测情况下，这导致了干预转换核的近似恢复；在部分可观测情况下，这表明了预测状态和信念状记忆的必要性，解决了先前世界模型恢复工作的开放问题。
英文摘要：
As artificial agents become increasingly capable, what internal structure is necessary for an agent to act competently under uncertainty? Classical results show that optimal control can be implemented using belief states or world models, but not that such representations are required. We prove quantitative "selection theorems" showing that strong task performance (low average-case regret) forces world models, belief-like memory and -- under task mixtures -- persistent regime-tracking variables resembling functional primitives of emotion, along with informational modularity under block-structured tasks. Our results cover stochastic policies, partial observability, and evaluation under task distributions, without assuming optimality, determinism, or access to an explicit model. Technically, we reduce predictive modeling to binary "betting" decisions and show that regret bounds limit probability mass on suboptimal bets, enforcing the predictive distinctions needed to separate high-margin outcomes. In fully observed settings, this yields approximate recovery of the interventional transition kernel; under partial observability, it implies necessity of predictive state and belief-like memory, addressing an open question in prior world-model recovery work.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
