mlsanityData to 14 Oct 2026

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

arXiv 2603.15658 ↗First posted 8 Mar 2026cs.AI cs.CL cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 8 Mar 2026.

Builds on

17 of 24 references.

References · 17

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  6. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  7. 2023Active Retrieval Augmented Generationcited by 516
  8. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  9. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  10. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 122
  11. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 119
  12. 2024SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedbackcited by 19
5 more
  1. 2024UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generationcited by 16
  2. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalizationcited by 9
  3. 2025RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learningcited by 6
  4. 2026Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrievalcited by 3
  5. 2025ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responsescited by 2

Built on by

Not cited yet.