提出结构化认证方法，让通用智能体在特定场景下可验证可靠性。
World Models in Pieces: Structural Certification for General Agents
- 基于局部转移的结构化认证框架，将目标性能映射到内部世界模型的逐项保证
- 算法在深度组合目标下筛选关键转移，实现误差上限为 $\mathcal{O}(1/n) + \mathcal{O}(δ)$
- 适用于需长期规划可靠性的通用智能体部署，尤其关注关键路径验证
在大世界设定中，智能体无法全知全能，其能力必然以碎片化方式分布在世界模型中。因此，标准的统一保障无法区分关键瓶颈与无关失败。我们首次形式化这一局限性，证明通用智能体非万能，导致标准最坏情况分析失去意义。为此，提出结构化认证——一种基于转移局部的框架，将有界目标条件性能转化为对智能体内部世界模型的逐项保证。主要贡献为构造性：提供算法，利用深度组合目标筛选特定转移，并证明在此类目标下，通用智能体的世界模型误差上界为 $\mathcal{O}(1/n) + \mathcal{O}(δ)$。反向地，该上界在小 $δ$ 范围内紧致，其存在性由我们的认证明确保证。这些结果使得通用智能体的可证部署成为可能，仅需定位长时程规划可靠的特定转移。
原文摘要 · Abstract (English)
In the big-world regime, agents cannot be universally capable and their ability is inevitably specialized across a world model in pieces. Consequently, standard uniform guarantees fail to distinguish between the understanding of critical bottlenecks and irrelevant failures. We first formalize this limitation by proving that general agents are not universal, rendering standard worst-case analysis uninformative. To overcome this, we introduce structural certification, a transition-local framework that maps bounded goal-conditioned performance to entry-wise guarantees on the agent's internal world model. Our main contribution is constructive. We provide algorithms that filter specific transitions using deep compositional goals and prove that a general agent on these goals has a structural world model with a $\mathcal{O}(1/n) + \mathcal{O}(δ)$ error bound. Conversely, this bound is tight in the small-$δ$ regime, whose existence is explicitly guaranteed by our certification. These results enable the certifiable deployment of general agents by localizing the specific transitions where long-horizon planning is reliable.
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。