提出按需选存器，提升记忆增强智能体效率与准确率
Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents
- 将记忆检索建模为路由决策问题，只选相关存储
- 相比均匀检索，减少大量上下文词元，准确率反而更高
- 适合构建高效可扩展的多存储智能体系统
记忆增强智能体维护多个专用存储，但现有系统对每个查询均从所有存储中检索，导致成本增加并引入无关上下文。本文将记忆检索建模为存储路由问题，并使用覆盖率、精确匹配率和词元效率指标进行评估。在下游问答任务中，基于最优策略的路由器在显著减少上下文词元使用的同时，实现了更高的准确率，表明选择性检索能同时提升效率与性能。结果表明，路由决策应作为记忆增强智能体设计的核心组成部分，并推动学习型路由机制以支持可扩展的多存储系统。此外，本文将存储选择形式化为一个权衡答案准确率与检索成本的成本敏感决策问题，为路由策略提供了原则性解释。
原文摘要 · Abstract (English)
Memory-augmented agents maintain multiple specialized stores, yet most systems retrieve from all stores for every query, increasing cost and introducing irrelevant context. We formulate memory retrieval as a store-routing problem and evaluate it using coverage, exact match, and token efficiency metrics. On downstream question answering, an oracle router achieves higher accuracy while using substantially fewer context tokens compared to uniform retrieval, demonstrating that selective retrieval improves both efficiency and performance. Our results show that routing decisions are a first-class component of memory-augmented agent design and motivate learned routing mechanisms for scalable multi-store systems. We additionally formalize store selection as a cost-sensitive decision problem that trades answer accuracy against retrieval cost, providing a principled interpretation of routing policies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。