MACTS-EM:带涌现记忆的多智能体时间序列预测框架
Get the story
2026年10月5日,arXiv Multiagent Systems 频道发布论文,提出 MACTS-EM 多智能体协同时间序列预测框架。该框架集成领域专用预测智能体、元认知层、涌现记忆机制、多模态上下文整合与对抗鲁棒性组件。论文称在金融市场、气候模式、能源消耗与疫情传播评估中,预测准确率提升8-12%,零样本迁移能力提升22-27%,状态转换期间韧性增强16-21%,分布偏移后恢复速度加快15-18%。目前公开信息仅见此一篇报道,尚无后续验证或独立复现结果。
Generated from reports · updated 16 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Multiagent SystemsMACTS-EM:带涌现记忆的多智能体协同时间序列预测框架
论文提出 MACTS-EM 多智能体协同时间序列预测框架,集成领域专用预测智能体、元认知层、涌现记忆机制、多模态上下文整合与对抗鲁棒性组件。在金融市场、气候模式、能源消耗与疫情传播评估中,预测准确率提升 8-12%,零样本迁移能力提升 22-27%,状态转换期间韧性增强 16-21%,分布偏移后恢复速度加快 15-18%。
Heat trend
Current heat 7·Comparable peak 10(Oct 5)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.