Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Hang, Zhang, Yongfeng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2404.09982
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910041209044992
author Gao, Hang
Zhang, Yongfeng
author_facet Gao, Hang
Zhang, Yongfeng
contents While Large Language Model (LLM) based agents excel at complex tasks, their performance in open-ended scenarios is often constrained by isolated operation and reliance on static databases, missing the dynamic knowledge exchange of human dialogue. To bridge this gap, we propose the INteractive Memory Sharing (INMS) framework, an asynchronous interaction paradigm for multi-agent systems. By integrating real-time memory filtering, storage, and retrieval, INMS establishes a shared conversational memory pool. This enables continuous, dialogue-like memory sharing among agents, promoting collective self-enhancement and dynamically refining the retrieval mediator based on interaction history. Extensive experiments across three datasets demonstrate that INMS significantly improves agent performance by effectively modeling multi-agent interaction and collective knowledge sharing.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09982
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle INMS: Memory Sharing for Large Language Model based Agents
Gao, Hang
Zhang, Yongfeng
Computation and Language
While Large Language Model (LLM) based agents excel at complex tasks, their performance in open-ended scenarios is often constrained by isolated operation and reliance on static databases, missing the dynamic knowledge exchange of human dialogue. To bridge this gap, we propose the INteractive Memory Sharing (INMS) framework, an asynchronous interaction paradigm for multi-agent systems. By integrating real-time memory filtering, storage, and retrieval, INMS establishes a shared conversational memory pool. This enables continuous, dialogue-like memory sharing among agents, promoting collective self-enhancement and dynamically refining the retrieval mediator based on interaction history. Extensive experiments across three datasets demonstrate that INMS significantly improves agent performance by effectively modeling multi-agent interaction and collective knowledge sharing.
title INMS: Memory Sharing for Large Language Model based Agents
topic Computation and Language
url https://arxiv.org/abs/2404.09982