Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failing when contexts shift or goals evolve. This paper argues that this failure is not technical but foundational: imitation learning has been optimised for the wrong objective. We propose a research agenda that redefines success from perfect replay to compositional adaptability. Such adaptability hinges on learning behavioural primitives once and recombining them through novel contexts without retraining. We establish metrics for compositional generalisation, propose hybrid architectures, and outline interdisciplinary research directions drawing on cognitive science and cultural evolution. Agents that embed adaptability at the core of imitation learning thus have an essential capability for operating in an open-ended world.

翻译：模仿学习正处于十字路口：尽管经过数十年的发展，当前的模仿学习智能体本质上仍是精密的记忆机器，擅长复现但无法应对情境迁移或目标演化。本文认为这一缺陷并非技术性问题，而是源于根本性原因：模仿学习长期以来被优化以实现错误的目标。我们提出一项研究议程，将成功标准从完美复现重新定义为组合适应性。这种适应性的关键在于一次性习得行为基元，并在未经重新训练的情况下通过新情境对其进行重组。我们建立了组合泛化的评估指标，提出了混合架构，并借鉴认知科学与文化演化理论勾勒出跨学科研究方向。将适应性内化为模仿学习核心的智能体，由此获得了在开放世界中运行的关键能力。