{"ID":5938108,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-13T23:59:41.726494204Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02881","arxiv_id":"2607.02881","title":"PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.02881","url_pdf":"https://arxiv.org/pdf/2607.02881v1","authors":"[\"Zhuoqun Li\",\"Boxi Cao\",\"Jiawei Chen\",\"Hanshu Zhou\",\"Ruoxi Xu\",\"Guiping Jiang\",\"Ruotong Pan\",\"Tingting Gao\",\"Han Li\",\"Xiangyu Wu\",\"Hongyu Lin\",\"Yaojie Lu\",\"Xianpei Han\",\"Le Sun\"]","published":"2026-07-03T02:25:48Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":614011,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5938108,"paper_url":"https://arxiv.org/abs/2607.02881","paper_title":"PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction","repo_url":"https://github.com/icip-cas/PraMem","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}