Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. However, existing designs almost exclusively adopt a centralized repository shared across agents, incurring communication and coordination overhead, raising privacy concerns, and collapsing agent diversity. We propose DecentMem, a decentralized memory framework in which each agent maintains its own dual-pool memory -- an exploitation pool of consolidated past trajectories and an exploration pool of LLM-generated candidates for unseen contexts. The two pools are reweighted online based on stage-wise feedback from an LLM-as-a-judge. Theoretically, we prove that this design guarantees global reachability of the solution space and achieves $O(\log T)$ cumulative regret, matching the stochastic bandit lower bound up to constants. In practice, across three MAS frameworks (AutoGen, DyLAN, AgentNet), three Qwen3 backbones (4B/8B/14B), two Gemma4 backbones (E2B/E4B) and five benchmarks spanning math, code, QA, and embodied tasks, DecentMem improves average accuracy by up to 23.8% over the strongest centralized memory baseline and by up to 52.5% over the no-memory baseline, while reducing token usage by up to 49%.

翻译：自我进化多智能体系统（MAS）已成为通过持续经验改进LLM智能体的一种有前景的途径，其基础在于持久记忆。然而，现有设计几乎全部采用跨智能体共享的集中式存储库，这带来了通信与协调开销、引发隐私问题，并导致智能体多样性丧失。我们提出DecentMem——一种分散式记忆框架，其中每个智能体维护自己的双池记忆：一个利用池，用于整合过往轨迹；一个探索池，用于生成LLM在未见上下文中候选方案。这两个池基于分阶段反馈（由LLM作为评判者）进行在线重新加权。理论上，我们证明该设计保证了解决方案空间的全局可达性，并实现了$O(\log T)$的累积遗憾，与随机赌博机下界在常数因子内匹配。在实践上，跨越三个MAS框架（AutoGen、DyLAN、AgentNet）、三个Qwen3主干（4B/8B/14B）、两个Gemma4主干（E2B/E4B）以及涵盖数学、编程、问答和具身任务的五个基准测试中，DecentMem相比最强的集中式记忆基线，平均准确率提升高达23.8%，相比无记忆基线提升高达52.5%，同时令牌使用量减少高达49%。