MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents
2026-07-28 • Databases
DatabasesArtificial Intelligence
AI summaryⓘ
The authors address the problem of managing memory for large language model (LLM) agents, where current methods treat all user interactions the same, causing inefficient memory use. They introduce MemLens, a system that evaluates and stores memories based on their value, helping to keep important information accessible while removing less useful data. MemLens offers a dashboard that lets users see how memories are stored and used, and compare different memory strategies to improve responses. This aims to make LLM agents smarter and more personalized over time.
memory managementlarge language modelsLLM agentsShapley valueinteractive dashboardmemory evaluationpersonalizationlong-term memoryresponse quality
Authors
Shuyue Wei, Chang Liu, Zimu Zhou, Yongxin Tong, Lizhen Cui
Abstract
Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized responses, and knowledge reuse. However, existing LLM memory systems typically adopt a coarse-grained (utility-agnostic) manner that treats heterogeneous user-LLM interaction records uniformly, leading to redundant and low-impact records persisting in the memory repository. To address this challenge, we present MemLens, a value-aware memory management system that takes memory records as first-class data objects. MemLens provides an end-to-end interactive analytics dashboard that exposes the complete memory lifecycle, including Shapley-style memory evaluation, value-aware storage, and memory-assisted response. Through a study-copilot application, the system enables users to inspect memory values, visualize hierarchical memory structures, and compare various memory management strategies in terms of response quality, retrieval latency, and token consumption. Therefore, our MemLens can serve as an efficient, interpretable, and personalized long-term memory management system for LLM-based agents.