Despite the explosive growth of AI and the technologies built upon it, predicting and inferring the sub-optimal behavior of users or human collaborators remains a critical challenge. In many cases, such behaviors are not a result of irrationality, but rather a rational decision made given inherent cognitive bounds and biased beliefs about the world. In this paper, we formally introduce a class of computational-rational (CR) user models for cognitively-bounded agents acting optimally under biased beliefs. The key novelty lies in explicitly modeling how a bounded memory process leads to a dynamically inconsistent and biased belief state and, consequently, sub-optimal sequential decision-making. We address the challenge of identifying the latent user-specific bound and inferring biased belief states from passive observations on the fly. We argue that for our formalized CR model family with an explicit and parameterized cognitive process, this challenge is tractable. To support our claim, we propose an efficient online inference method based on nested particle filtering that simultaneously tracks the user's latent belief state and estimates the unknown cognitive bound from a stream of observed actions. We validate our approach in a representative navigation task using memory decay as an example of a cognitive bound. With simulations, we show that (1) our CR model generates intuitively plausible behaviors corresponding to different levels of memory capacity, and (2) our inference method accurately and efficiently recovers the ground-truth cognitive bounds from limited observations ($\le 100$ steps). We further demonstrate how this approach provides a principled foundation for developing adaptive AI assistants, enabling adaptive assistance that accounts for the user's memory limitations.

翻译：尽管人工智能及其相关技术呈现爆炸式增长，但预测和推断用户或人类协作者的次优行为仍是一个关键挑战。在许多情况下，此类行为并非源于非理性，而是在固有认知局限和对世界的偏差信念下做出的理性决策。本文正式提出一类针对认知受限主体的计算理性用户模型，这些主体在偏差信念下以最优方式行动。其核心创新在于显式建模了受限记忆过程如何导致动态不一致且存在偏差的信念状态，进而引发次优的序列决策。我们解决了从被动观察中实时识别潜在用户特定认知界限并推断偏差信念状态的挑战。我们认为，对于这种具有显式参数化认知过程的计算理性模型族，该挑战是可处理的。为支持这一主张，我们提出一种基于嵌套粒子滤波的高效在线推断方法，该方法能同时追踪用户的潜在信念状态，并从观测到的动作流中估计未知的认知界限。我们在具有代表性的导航任务中，以记忆衰减作为认知界限的实例验证了所提方法。通过仿真实验，我们证明：（1）计算理性模型能生成与不同记忆容量水平相对应的直观合理行为；（2）推断方法能够从有限观测步数（≤100步）中准确高效地还原真实认知界限。我们进一步阐述了该方法如何为开发自适应人工智能助手提供理论基础，从而实现能够适应用户记忆局限性的自适应辅助。