BMAM：类脑多智能体记忆框架

摘要

基于语言模型的智能体在长程交互中持续面临两大挑战：如何保持时序关联信息的完整性，以及如何维持跨会话的行为一致性——我们将这种失效模式称为"灵魂侵蚀"。本文提出BMAM（类脑多智能体记忆架构），该通用记忆架构将智能体记忆建模为功能专精的子系统集合，而非单一非结构化存储。受认知记忆系统启发，BMAM将记忆解构为情景记忆、语义记忆、显著性感知与控制导向四大组件，各组件在互补的时间尺度上运作。为支持长程推理，BMAM沿显性时间轴组织情景记忆，并通过融合多重互补信号进行证据检索。在LoCoMo基准测试中，BMAM在标准长程评估设定下达到78.45%的准确率，消融实验证实受海马体启发的的情景记忆子系统对时序推理具有关键作用。

English

Language-model-based agents operating over extended interaction horizons face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions, a failure mode we term soul erosion. We present BMAM (Brain-inspired Multi-Agent Memory), a general-purpose memory architecture that models agent memory as a set of functionally specialized subsystems rather than a single unstructured store. Inspired by cognitive memory systems, BMAM decomposes memory into episodic, semantic, salience-aware, and control-oriented components that operate at complementary time scales. To support long-horizon reasoning, BMAM organizes episodic memories along explicit timelines and retrieves evidence by fusing multiple complementary signals. Experiments on the LoCoMo benchmark show that BMAM achieves 78.45 percent accuracy under the standard long-horizon evaluation setting, and ablation analyses confirm that the hippocampus-inspired episodic memory subsystem plays a critical role in temporal reasoning.

BMAM：类脑多智能体记忆框架

BMAM: Brain-inspired Multi-Agent Memory Framework

摘要

Support