G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

TL;DR

G-Memory introduces a hierarchical, graph-based memory system for multi-agent systems that enhances collaboration and knowledge retention, significantly improving task success and accuracy across multiple benchmarks without altering existing frameworks.

Contribution

It presents G-Memory, a novel hierarchical memory architecture inspired by organizational memory theory, tailored for multi-agent systems to improve their self-evolution and collaboration capabilities.

Findings

Up to 20.89% improvement in success rates for embodied actions.

Up to 10.12% increase in knowledge QA accuracy.

Effective across multiple benchmarks, LLM backbones, and MAS frameworks.

Abstract

Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory architectures. Upon close inspection, we are alarmed to discover that prevailing MAS memory mechanisms (1) are overly simplistic, completely disregarding the nuanced inter-agent collaboration trajectories, and (2) lack cross-trial and agent-specific customization, in stark contrast to the expressive memory developed for single agents. To bridge this gap, we introduce G-Memory, a hierarchical, agentic memory system for MAS inspired by organizational memory theory, which manages the lengthy MAS interaction via a three-tier graph hierarchy: insight, query, and interaction graphs. Upon receiving a new user query, G-Memory performs bi-directional memory traversal to retrieve both $\textit{high-level, generalizable insights}$ that enable the system to leverage cross-trial knowledge, and $\textit{fine-grained, condensed interaction trajectories}$ that compactly encode prior collaboration experiences. Upon task execution, the entire hierarchy evolves by assimilating new collaborative trajectories, nurturing the progressive evolution of agent teams. Extensive experiments across five benchmarks, three LLM backbones, and three popular MAS frameworks demonstrate that G-Memory improves success rates in embodied action and accuracy in knowledge QA by up to $20.89\%$ and $10.12\%$, respectively, without any modifications to the original frameworks. Our codes are available at https://github.com/bingreeky/GMemory.