通用代理記憶體制之深度研究

摘要

记忆对于人工智能代理至关重要，然而广泛采用的静态记忆，旨在预先创建随时可用的记忆，不可避免地会遭受严重的信息损失。为解决这一局限，我们提出了一种名为通用代理记忆（GAM）的新框架。GAM遵循“即时编译（JIT）”原则，在运行时专注于为其客户端创建优化的上下文，同时在离线阶段仅保留简单但有用的记忆。为此，GAM采用了一种双重设计，包含以下组件：1）记忆器，通过轻量级记忆突出关键历史信息，同时在通用页面存储中维护完整的历史信息；2）研究者，根据预先构建的记忆，从页面存储中检索并整合有用信息以响应在线请求。这一设计使GAM能够有效利用前沿大型语言模型（LLMs）的代理能力和测试时扩展性，同时通过强化学习促进端到端的性能优化。在我们的实验研究中，我们展示了GAM在各种基于记忆的任务完成场景中相较于现有记忆系统取得的显著改进。

English

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 general agentic memory (GAM). GAM follows the principle of "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) Memorizer, which highlights key historical information using a lightweight memory, while maintaining complete historical information within a universal page-store. 2) 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.

通用代理記憶體制之深度研究

General Agentic Memory Via Deep Research

摘要

Support