← Back ◬ AI & Machine Learning —

Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents

arXiv AI Archived Mar 18, 2026 ✓ Full text saved

arXiv:2603.15658v1 Announce Type: new Abstract: 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 retr

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Artificial Intelligence [Submitted on 8 Mar 2026] Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents Madhava Gaikwad 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. Comments: accepted in ICLR 2026 Workshop on Memory for LLM-Based Agentic Systems Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) MSC classes: 2020: 68T30, 68T20 ACM classes: H.3.3; I.2.11 Cite as: arXiv:2603.15658 [cs.AI] (or arXiv:2603.15658v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2603.15658 Focus to learn more Submission history From: Madhava Gaikwad [view email] [v1] Sun, 8 Mar 2026 09:12:30 UTC (25 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev | next > new | recent | 2026-03 Change to browse by: cs cs.CL cs.IR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes