发表机构
Beijing Academy of Artificial Intelligence; Peking University; Hong Kong Polytechnic University（北京人工智能研究院; 北京大学; 香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有代理记忆系统提前构建记忆可能丢失重要信息的问题，本文提出即时代理记忆（JAM）框架，通过运行时查询条件化上下文构建，并在多个基准上实现优于AOT系统且更高效的任务性能。
AI 中文摘要
记忆对于AI代理至关重要。许多现有的代理记忆系统采用提前（AOT）设计，在特定请求到达之前构建记忆。虽然这降低了在线服务成本，但这种与请求无关的记忆构建可能会丢弃后来变得重要的细粒度信息。为了解决这一局限性，我们提出了即时代理记忆（JAM），一个可训练的框架，用于在运行时进行查询条件化的上下文构建。一个记忆器在具有紧凑导航摘要的分层页面存储中保留完整的原始历史，而一个研究者迭代地检索、检查并整合每个请求的证据。为了训练这些记忆使用行为，我们引入了Memory-Gym，一个基于证据的数据合成流程，涵盖六个领域的九种任务类型，并通过验证轨迹监督微调，随后进行提示引导的组相对策略优化来优化研究者。我们在各种代理记忆和长上下文处理的基准上展示了JAM的有效性，在这些基准上，它比AOT风格的记忆系统实现了更强的任务性能，同时比先前训练的代理记忆方法保持显著更高的效率。为了支持可复现性和未来研究，我们在此https URL发布我们的匿名源代码。
英文摘要
Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific request arrives. While this reduces online serving cost, such request-agnostic memory construction can discard fine-grained information that later becomes important. To address this limitation, we propose Just-In-Time Agent Memory (JAM), a trainable framework for query-conditioned context construction at runtime. A Memorizer preserves complete raw histories in a hierarchical page-store with compact navigational summaries, while a Researcher iteratively retrieves, inspects, and integrates evidence for each request. To train these memory-use behaviors, we introduce Memory-Gym, an evidence-grounded data synthesis pipeline covering nine task types across six domains, and optimize the Researcher through verified-trajectory supervised fine-tuning followed by Hint-guided Group Relative Policy Optimization. We demonstrate the effectiveness of JAM across a variety of benchmarks on agent memory and long-context processing, where it achieves stronger task performance than AOT-style memory systems while remaining substantially more efficient than prior trained agentic memory approaches. To support reproducibility and future research, we release our anonymized source code at https://github.com/VectorSpaceLab/general-agentic-memory.
