SEDM: Scalable Self-Evolving Distributed Memory for Agents
This addresses scalability and performance issues for multi-agent systems, though it appears incremental as it builds on existing memory methods with novel optimizations.
The paper tackles the problem of inefficient memory management in long-term multi-agent systems, which suffer from noise accumulation and uncontrolled expansion, by introducing SEDM, a self-evolving distributed memory framework that improves reasoning accuracy and reduces token overhead compared to baselines.
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.