Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Haoran, Hu, Jiacong, Zhang, Ke, Yu, Lei, Tang, Yuxin, Song, Xinyuan, Duan, Yiqun, Ai, Lynn, Shi, Bill
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.09498
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908560234905600
author Xu, Haoran
Hu, Jiacong
Zhang, Ke
Yu, Lei
Tang, Yuxin
Song, Xinyuan
Duan, Yiqun
Ai, Lynn
Shi, Bill
author_facet Xu, Haoran
Hu, Jiacong
Zhang, Ke
Yu, Lei
Tang, Yuxin
Song, Xinyuan
Duan, Yiqun
Ai, Lynn
Shi, Bill
contents Long-term multi-agent systems inevitably generate vast amounts of trajectories and historical interactions, which makes efficient memory management essential for both performance and scalability. Existing methods typically depend on vector retrieval and hierarchical storage, yet they are prone to noise accumulation, uncontrolled memory expansion, and limited generalization across domains. To address these challenges, we present SEDM, Self-Evolving Distributed Memory, a verifiable and adaptive framework that transforms memory from a passive repository into an active, self-optimizing component. SEDM integrates verifiable write admission based on reproducible replay, a self-scheduling memory controller that dynamically ranks and consolidates entries according to empirical utility, and cross-domain knowledge diffusion that abstracts reusable insights to support transfer across heterogeneous tasks. Evaluations on benchmark datasets demonstrate that SEDM improves reasoning accuracy while reducing token overhead compared with strong memory baselines, and further enables knowledge distilled from fact verification to enhance multi-hop reasoning. The results highlight SEDM as a scalable and sustainable memory mechanism for open-ended multi-agent collaboration. The code will be released in the later stage of this project.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09498
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEDM: Scalable Self-Evolving Distributed Memory for Agents
Xu, Haoran
Hu, Jiacong
Zhang, Ke
Yu, Lei
Tang, Yuxin
Song, Xinyuan
Duan, Yiqun
Ai, Lynn
Shi, Bill
Artificial Intelligence
Long-term multi-agent systems inevitably generate vast amounts of trajectories and historical interactions, which makes efficient memory management essential for both performance and scalability. Existing methods typically depend on vector retrieval and hierarchical storage, yet they are prone to noise accumulation, uncontrolled memory expansion, and limited generalization across domains. To address these challenges, we present SEDM, Self-Evolving Distributed Memory, a verifiable and adaptive framework that transforms memory from a passive repository into an active, self-optimizing component. SEDM integrates verifiable write admission based on reproducible replay, a self-scheduling memory controller that dynamically ranks and consolidates entries according to empirical utility, and cross-domain knowledge diffusion that abstracts reusable insights to support transfer across heterogeneous tasks. Evaluations on benchmark datasets demonstrate that SEDM improves reasoning accuracy while reducing token overhead compared with strong memory baselines, and further enables knowledge distilled from fact verification to enhance multi-hop reasoning. The results highlight SEDM as a scalable and sustainable memory mechanism for open-ended multi-agent collaboration. The code will be released in the later stage of this project.
title SEDM: Scalable Self-Evolving Distributed Memory for Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2509.09498