arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.04503cs.AIcs.MA
收藏

记忆智能代理

Memory Intelligence Agent

East China Normal University(华东师范大学);Shanghai Innovation Institute(上海创新研究院);Harbin Institute of Technology(哈尔滨工业大学);Xiamen University(厦门大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Independent Researcher(独立研究者)

Jingyang Qiao, Weicheng Meng, Yu Cheng, Zhihang Lin, Zhizhong Zhang, Xin Tan, Jingyu Gong, Kun Shao, Yuan Xie

AI总结:

本文提出Memory Intelligence Agent框架,通过Manager-Planner-Executor架构实现高效记忆演化,结合强化学习与双向记忆转换,提升推理与自进化能力。

摘要:

本文提出Memory Intelligence Agent框架,通过Manager-Planner-Executor架构实现高效记忆演化,结合强化学习与双向记忆转换,提升推理与自进化能力。

英文摘要:

Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning and autonomous evolution. Existing methods rely on retrieving similar trajectories from memory to aid reasoning, while suffering from key limitations of ineffective memory evolution and increasing storage and retrieval costs. To address these problems, we propose a novel Memory Intelligence Agent (MIA) framework, consisting of a Manager-Planner-Executor architecture. Memory Manager is a non-parametric memory system that can store compressed historical search trajectories. Planner is a parametric memory agent that can produce search plans for questions. Executor is another agent that can search and analyze information guided by the search plan. To build the MIA framework, we first adopt an alternating reinforcement learning paradigm to enhance cooperation between the Planner and the Executor. Furthermore, we enable the Planner to continuously evolve during test-time learning, with updates performed on-the-fly alongside inference without interrupting the reasoning process. Additionally, we establish a bidirectional conversion loop between parametric and non-parametric memories to achieve efficient memory evolution. Finally, we incorporate a reflection and an unsupervised judgment mechanisms to boost reasoning and self-evolution in the open world. Extensive experiments across eleven benchmarks demonstrate the superiority of MIA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑