Search papers, labs, and topics across Lattice.
This paper introduces PraMem, a novel approach that transforms lengthy historical sequences from a burden into a valuable resource for long-horizon behavior prediction by leveraging experiential memory built through prior practice. Unlike traditional memory management methods that compress context, PraMem enhances prediction accuracy by utilizing this experiential memory as an assisted input. Extensive experiments reveal that PraMem outperforms existing methods, providing deeper insights into the mechanisms governing experiential memory evolution.
Transforming historical sequences into a powerful resource, PraMem significantly improves long-horizon behavior prediction beyond existing methods.
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. 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. 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. Code: https://github.com/icip-cas/PraMem.
