In this work, we identify and address the core challenges of agentic memory management in LLM serving, where large-scale storage, frequent updates, and multiple coexisting agents jointly introduce complex and high-cost approximate nearest neighbor (ANN) searching problems. We present Pancake, a multi-tier agentic memory system that unifies three key techniques: (i) multi-level index caching for single agents, (ii) coordinated index management across multiple agents, and (iii) collaborative GPU-CPU acceleration. Pancake exposes easy-to-use interface that can be integrated into memory-based agents like Mem-GPT, and is compatible with agentic frameworks such as LangChain and LlamaIndex. Experiments on realistic agent workloads show that Pancake substantially outperforms existing frameworks, achieving more than 4.29x end-to-end throughput improvement.
@article{arxiv.2602.21477,
title = {Pancake: Hierarchical Memory System for Multi-Agent LLM Serving},
author = {Zhengding Hu and Zaifeng Pan and Prabhleen Kaur and Vibha Murthy and Zhongkai Yu and Yue Guan and Zhen Wang and Steven Swanson and Yufei Ding},
journal= {arXiv preprint arXiv:2602.21477},
year = {2026}
}