Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents
This addresses cost and performance issues in scalable multi-store systems for AI agents, though it is incremental as it builds on existing memory-augmented architectures.
The paper tackled the problem of inefficient memory retrieval in memory-augmented agents by formulating store routing to selectively retrieve from specialized stores, resulting in higher accuracy and substantially fewer context tokens compared to uniform retrieval.
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.