PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction

PraMem：用于长程行为预测的实践衍生经验记忆

Long-horizon behavior prediction aims to infer a user’s next action based on a lengthy historical sequence, playing a crucial role in artificial intelligence field. The rise of large language models (LLMs) offers a promising direction for sequential behavior prediction, yet LLMs struggle with latent behavioral pattern induction and model-intrinsic cognitive biases when tackling long-horizon behavior prediction. 长程行为预测旨在根据冗长的历史序列推断用户的下一个动作，这在人工智能领域发挥着至关重要的作用。大型语言模型（LLMs）的兴起为序列行为预测提供了一个有前景的方向，然而，当处理长程行为预测时，LLMs 在潜在行为模式归纳和模型固有的认知偏差方面仍面临挑战。

Prior memory management methods follow a context-compression paradigm that attempts to address this task by alleviating the historical sequence burden, yet fail to resolve the core challenges. In this paper, we advocate a paradigm shift that reframes the lengthy historical sequence from a burden into a valuable resource to be exploited, and accordingly propose PraMem, which conducts beforehand practice over the lengthy historical sequence to build an experiential memory, thereby serving as the assisted input for accurate long-horizon behavior prediction. 先前的记忆管理方法遵循一种上下文压缩范式，试图通过减轻历史序列的负担来解决这一任务，但未能从根本上解决核心挑战。在本文中，我们提倡一种范式转变，将冗长的历史序列从一种负担重新定义为一种可利用的宝贵资源。据此，我们提出了 PraMem，它通过对冗长的历史序列进行预先实践来构建经验记忆，从而为准确的长程行为预测提供辅助输入。

Extensive experiments across diverse tasks demonstrate that PraMem achieves superior performance than prior methods, and more in-depth analyses provide valuable insights into the mechanism and evolution of the experiential memory. 在多项任务上的广泛实验表明，PraMem 取得了优于现有方法的效果，更深入的分析也为经验记忆的机制和演化提供了有价值的见解。