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

NeurIPSSpotlight2025

Authors
Guibin Zhang, Muxin Fu, Kun Wang, Guancheng Wan, Miao Yu, Shuicheng YAN
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

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 re…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

large language model language model memory agent llm

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive