{"ID":2837998,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18423","arxiv_id":"2511.18423","title":"General Agentic Memory Via Deep Research","abstract":"Memory is critical for AI agents, yet the widely-adopted static memory, aiming to create readily available memory in advance, is inevitably subject to severe information loss. To address this limitation, we propose a novel framework called \\textbf{general agentic memory (GAM)}. GAM follows the principle of \"\\textbf{just-in time (JIT) compilation}\" where it focuses on creating optimized contexts for its client at runtime while keeping only simple but useful memory during the offline stage. To this end, GAM employs a duo-design with the following components. 1) \\textbf{Memorizer}, which highlights key historical information using a lightweight memory, while maintaining complete historical information within a universal page-store. 2) \\textbf{Researcher}, which retrieves and integrates useful information from the page-store for its online request guided by the pre-constructed memory. This design allows GAM to effectively leverage the agentic capabilities and test-time scalability of frontier large language models (LLMs), while also facilitating end-to-end performance optimization through reinforcement learning. In our experimental study, we demonstrate that GAM achieves substantial improvement on various memory-grounded task completion scenarios against existing memory systems.","short_abstract":"Memory is critical for AI agents, yet the widely-adopted static memory, aiming to create readily available memory in advance, is inevitably subject to severe information loss. To address this limitation, we propose a novel framework called \\textbf{general agentic memory (GAM)}. GAM follows the principle of \"\\textbf{jus...","url_abs":"https://arxiv.org/abs/2511.18423","url_pdf":"https://arxiv.org/pdf/2511.18423v1","authors":"[\"B. Y. Yan\",\"Chaofan Li\",\"Hongjin Qian\",\"Shuqi Lu\",\"Zheng Liu\"]","published":"2025-11-23T12:29:33Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.IR\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}