Are We Ready For An Agent-Native Memory System?

2026-06-23

AI Summary

This study addresses the lack of fine-grained, system-level evaluation in existing memory systems for large language model agents, which hinders robust assessment under cost constraints, architectural trade-offs, and dynamic knowledge updates. The work proposes a unified analytical framework by decomposing agent memory into four independently evaluable core modules: representation storage, extraction, retrieval routing, and maintenance. Through end-to-end and ablation experiments across twelve representative systems, multi-benchmark workload evaluations and cost-performance analyses reveal that memory architectures must align with task-specific bottlenecks and quantify each module’s contribution to overall performance. Key findings indicate no single architecture universally dominates; instead, localized maintenance strategies consistently outperform global reorganization, offering superior cost-effectiveness and guiding the design of agent-native memory systems.

Abstract

Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information storage, retrieval, update, consolidation, and dynamic lifecycle governance throughout agent execution. Despite this evolution, existing evaluations still benchmark agent memory mainly through end-to-end task success metrics (e.g., F1, BLEU), while treating the underlying system as a monolithic black box. As a result, critical system-level concerns, including operational costs, architectural trade-offs across memory modules, and robustness under dynamic knowledge updates, remain insufficiently explored. In this paper, we present a systematic experimental study of agent memory from a data management perspective. We propose an analytical framework that decomposes agent memory into four core modules: memory representation and storage, extraction, retrieval and routing, and maintenance. Under this framework, we evaluate 12 representative memory systems and two reference baselines across five benchmark workloads spanning 11 datasets. Our extensive end-to-end evaluation shows that no single architecture dominates across all scenarios; instead, effectiveness depends heavily on how well the memory structure aligns with the workload bottleneck. Furthermore, through fine-grained ablation studies, we quantify their individual effects on representation fidelity, retrieval precision, update correctness, and long-horizon stability. Finally, we reveal cost-performance trade-offs under realistic workloads, showing localized maintenance is more cost-efficient than global reorganization. Based on these findings, we identify promising directions towards building truly agent-native memory systems. The code is publicly available at https://github.com/OpenDataBox/MemoryData.

Problem

• agent memory
• data management
• system evaluation
• memory architecture
• dynamic knowledge update

Innovation

• agent-native memory
• memory system evaluation
• data management perspective
• modular memory architecture
• cost-performance trade-off