MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents
Summary: MemLens treats LLM-agent memories as first-class data, using Shapley-style value assessment for value-aware storage and retrieval. Its interactive dashboard visualizes memory lifecycles and hierarchies, enabling interpretable strategy comparisons across quality, latency, and token cost. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Shuyue Wei (Shandong University)
- 2. Chang Liu (Beihang University)
- 3. Zimu Zhou (City University of Hong Kong)
- 4. Yongxin Tong (Beihang University)
- 5. Lizhen Cui (Shandong University)
BibTeX Citation
@article{wei_vldb26,
title = {{MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents}},
author = {Wei, Shuyue and Liu, Chang and Zhou, Zimu and Tong, Yongxin and Cui, Lizhen},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4606--4609},
doi = {10.14778/3827998.3828077},
url = {https://doi.org/10.14778/3827998.3828077},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,338 | VikingMem: A Memory Base Management System for Stateful LLM-based Applications | 2026 | VLDB | 5.8092399e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 13,605 | Hypothesis Exploration with LLM-driven Intelligent Orchestration System | 2026 | VLDB |
| 2 | 5,149 | LLM for Data Management | 2024 | VLDB |
| 3 | 7,318 | An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models | 2024 | VLDB |
| 4 | 9,395 | MemFlow: Memory-Aware Distributed Deep Learning | 2020 | SIGMOD |
| 5 | 10,776 | Efficient Cooperation-Aware Key and Value Management for LLM Inference | 2026 | VLDB |
| 6 | 9,444 | Intelligent Agents for Data Exploration | 2024 | VLDB |
| 7 | 11,148 | Demo of LearnedWMP: Workload Memory Prediction Using Deep Query Template Representations | 2025 | SIGMOD |
| 8 | 10,042 | MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training | 2025 | SIGMOD |
| 9 | 13,609 | Data Management for Agentic Memory: Foundations, Systems, and Challenges | 2026 | VLDB |
| 10 | 6,338 | VikingMem: A Memory Base Management System for Stateful LLM-based Applications | 2026 | VLDB |