# KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning

arXiv: https://arxiv.org/abs/2602.23592 · HTML: https://mlsanity.com/paper/2602.23592/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 20 of 20)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion](https://mlsanity.com/paper/2405.16444/) (2024)
- [ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference](https://mlsanity.com/paper/2410.21465/) (2024)
- [Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization](https://mlsanity.com/paper/2308.02151/) (2023)
- [MemGen: Weaving Generative Latent Memory for Self-Evolving Agents](https://mlsanity.com/paper/2509.24704/) (2025)
- [ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2502.00299/) (2025)
- [KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows](https://mlsanity.com/paper/2507.07400/) (2025)
- [EPIC: Efficient Position-Independent Caching for Serving Large Language Models](https://mlsanity.com/paper/2410.15332/) (2024)
- [KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems](https://mlsanity.com/paper/2409.14908/) (2024)
- [Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents](https://mlsanity.com/paper/2509.23040/) (2025)
- [Robix: A Unified Model for Robot Interaction, Reasoning and Planning](https://mlsanity.com/paper/2509.01106/) (2025)
- [FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference](https://mlsanity.com/paper/2505.13109/) (2025)
- [LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design](https://mlsanity.com/paper/2502.15260/) (2025)
- [CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering](https://mlsanity.com/paper/2506.11418/) (2025)
- [EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval](https://mlsanity.com/paper/2510.18546/) (2025)
- [Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU](https://mlsanity.com/paper/2506.20187/) (2025)

## Built on by (most cited first, 5 of 5)

- [Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse](https://mlsanity.com/paper/2606.23581/) (2026)
- [Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV](https://mlsanity.com/paper/2607.23693/) (2026)
- [BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents](https://mlsanity.com/paper/2609.08566/) (2026)
- [Positions Are Not Facts: The Mismatch Between KV Caches and Memory](https://mlsanity.com/paper/2609.33759/) (2026)
- [MIND: Instruction-Conditioned Incremental Grounding for Robots](https://mlsanity.com/paper/2610.19262/) (2026)

## Abstract (arXiv)

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping track of past experiences and environmental states, memory enables LLMs to maintain a global view, thereby avoiding repetitive exploration. However, existing approaches often store the memory as raw text, leading to excessively long prompts and high prefill latency. While it is possible to store and reuse the KV caches, the efficiency benefits are greatly undermined due to frequent KV cache updates. In this paper, we propose KEEP, a KV-cache-centric memory management system for efficient embodied planning. KEEP features 3 key innovations: (1) a Static-Dynamic Memory Construction algorithm that reduces KV cache recomputation by mixed-granularity memory group; (2) a Multi-hop Memory Re-computation algorithm that dynamically identifies important cross-attention among different memory groups and reconstructs memory interactions iteratively; (3) a Layer-balanced Memory Loading that eliminates unbalanced KV cache loading and cross-attention computation across different layers. Extensive experimental results have demonstrated that KEEP achieves 2.68x speedup with negligible accuracy loss compared with text-based memory methods on ALFRED dataset. Compared with the KV re-computation method CacheBlend (EuroSys'25), KEEP shows 4.13% success rate improvement and 1.90x time-to-first-token (TTFT) reduction. Our code is available on https://github.com/PKU-SEC-Lab/KEEP_Embodied_Memory.