世界模型应该遗忘什么？面向持续适应的分层保留

中文摘要 AI 辅助

持续学习将先前见过的数据上的性能退化视为失败的证据，这一惯例继承自预测目标静止不变的设置，其中正确的标签永远正确。世界模型不满足这一条件。它们的预测目标是环境，而环境是变化的，因此获取时准确的知识后来可能变得错误，丢弃这些知识是必要的行为而非缺陷。非平稳的真实标签在概念漂移文献和语言模型的时间事实性研究中已被充分探讨，但尚未针对世界模型进行系统阐述，世界模型的独特之处在于它们还编码了绝不能修订的知识。我们认为，持续世界模型需要按不变性时间尺度进行分层保留，将诸如物理和物体恒存性等绝不能修订的不变量，与应在环境变化时立即修订的实例级事实区分开来。标准的遗忘指标无法区分一个正确修订了过时知识的世界模型与一个遭受灾难性遗忘的世界模型，因而会将冻结的模型评为最高，而现有的物理推理基准仅评估冻结的检查点。我们提出差分保留，它在适应流上联合报告不变量的回归测试与修订延迟，而不进行聚合。

英文摘要

Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. World models do not satisfy this condition. Their prediction target is the environment, which changes, so knowledge that was accurate when acquired may later become false, and discarding it is required behavior rather than a defect. Non-stationary ground truth is well studied in the concept drift literature and in the temporal factuality of language models, but has not been formulated for world models, which are distinctive in that they also encode knowledge that must never be revised. We argue that continual world models require retention stratified by invariance timescale, separating invariants such as physics and object permanence, which must never be revised, from instance-level facts that should be revised as soon as the environment changes. Standard forgetting metrics cannot distinguish a world model that has correctly revised outdated knowledge from one that has suffered catastrophic forgetting, and consequently rank a frozen model highest, while existing physical-reasoning benchmarks evaluate only frozen checkpoints. We propose differential retention, which reports invariant regression testing across the adaptation stream jointly with revision latency, without aggregation.

发表机构

• University of Maryland, College Park（马里兰大学学院公园分校）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

Accepted to NeurIPS 2026 Continual World Models Workshop