Clustering-driven Memory Compression for On-device Large Language Models

• URL: http://arxiv.org/abs/2601.17443v1
• Date: Sat, 24 Jan 2026 12:31:15 GMT
• Title: Clustering-driven Memory Compression for On-device Large Language Models
• Abstract summary: We introduce a memory compression strategy that balances context efficiency and personalization quality.<n>Our method groups memories by similarity and merges them within clusters prior to concatenation.<n>Experiments demonstrate that our approach substantially lowers the number of memory tokens while outperforming baseline strategies.
• Score: 36.84681161552071
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) often rely on user-specific memories distilled from past interactions to enable personalized generation. A common practice is to concatenate these memories with the input prompt, but this approach quickly exhausts the limited context available in on-device LLMs. Compressing memories by averaging can mitigate context growth, yet it frequently harms performance due to semantic conflicts across heterogeneous memories. In this work, we introduce a clustering-based memory compression strategy that balances context efficiency and personalization quality. Our method groups memories by similarity and merges them within clusters prior to concatenation, thereby preserving coherence while reducing redundancy. Experiments demonstrate that our approach substantially lowers the number of memory tokens while outperforming baseline strategies such as naive averaging or direct concatenation. Furthermore, for a fixed context budget, clustering-driven merging yields more compact memory representations and consistently enhances generation quality.

Related papers

• Collaborative Memory Augmentation for Generative Recommendation [49.76630658239287]
  We propose textbfOMEGA, a cOllaborative MEmory augmentation framework for Generative recommendAtion.<n>We first introduce a latent context compression method that utilizes learnable query tokens to distill sequential user behavior into compact representations.<n>These compressed representations are aggregated into a collaborative memory bank, serving as an explicit repository of global behavioral patterns.
  arXiv  Detail & Related papers  (2026-08-02T15:34:43Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents [16.625864201773343]
  RecMem stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval.<n>Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.
  arXiv  Detail & Related papers  (2026-05-15T15:17:36Z)
• CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents [14.554199342275588]
  We introduce CLAG, a CLustering-based AGentic memory framework where an SLM agent actively organizes memory by clustering.<n>By performing localized evolution within these structured neighborhoods, CLAG effectively reduces cross-topic interference and enhances internal memory density.<n> Experiments on multiple QA datasets with three SLM backbones show that CLAG consistently improves answer quality and robustness over prior memory systems for agents, remaining lightweight and efficient.
  arXiv  Detail & Related papers  (2026-03-16T15:30:20Z)
• HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling [7.24393498822329]
  HyMem is a hybrid memory architecture that enables dynamic on-demand scheduling through multi-granular memory representations.<n>We show that HyMem achieves strong performance on both the LOCOMO and LongMemEval benchmarks, outperforming full-context while reducing computational cost by 92.6%.
  arXiv  Detail & Related papers  (2026-02-15T00:06:19Z)
• UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory [46.87954895079213]
  Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)<n>Existing methods predominately optimize memory management while treating memory extraction as a static process.<n>We propose Unified Memory Extraction and Management (UMEM) to jointly optimize a Large Language Model to simultaneous extract and manage memories.
  arXiv  Detail & Related papers  (2026-02-11T08:58:41Z)
• LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering [52.41664454251679]
  Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering.<n>Existing methods often rely on complex pipelines with external modules, sacrificing a truly end-to-end approach.<n>We introduce LLM-MemCluster, a novel framework that reconceptualizes clustering as a fully LLM-native task.
  arXiv  Detail & Related papers  (2025-11-19T13:22:08Z)
• CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling [52.05149789178508]
  CCF is a novel context compression framework designed to enable efficient long-context modeling.<n>CCF integrates segment-wise semantic aggregation with key-value memory encoding, forming compact representations.<n> Empirical results on multiple long-context language modeling benchmarks demonstrate that CCF achieves competitive perplexity under high compression ratios.
  arXiv  Detail & Related papers  (2025-09-11T07:13:49Z)
• From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents [79.87304940020256]
  Large Language Models (LLMs) have been widely adopted in conversational agents.<n>MemGAS is a framework that enhances memory consolidation by constructing multi-granularity association, adaptive selection, and retrieval.<n> Experiments on four long-term memory benchmarks demonstrate that MemGAS outperforms state-of-the-art methods on both question answer and retrieval tasks.
  arXiv  Detail & Related papers  (2025-05-26T06:13:07Z)
• Cognitive Memory in Large Language Models [8.059261857307881]
  This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency.<n>It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures.
  arXiv  Detail & Related papers  (2025-04-03T09:58:19Z)
• CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory [38.429707659685974]
  Large Language Models (LLMs) struggle to handle long input sequences due to high memory and runtime costs. We introduce an associative memory module which can be coupled to any pre-trained (frozen) attention-based LLM without re-training. This architecture, which we call CAMELoT, demonstrates superior performance even with a tiny context window of 128 tokens.
  arXiv  Detail & Related papers  (2024-02-21T01:00:17Z)
• Dual Cluster Contrastive learning for Person Re-Identification [78.42770787790532]
  We formulate a unified cluster contrastive framework, named Dual Cluster Contrastive learning (DCC) DCC maintains two types of memory banks: individual and centroid cluster memory banks. It can be easily applied for unsupervised or supervised person ReID.
  arXiv  Detail & Related papers  (2021-12-09T02:43:25Z)
• Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems [27.419109620575313]
  A key challenge for deep learning models is to work with millions of categorical classes or tokens. We propose a novel formulation of memory shared embedding, where memory is shared in proportion to the overlap in semantic information. We demonstrate a significant reduction in the memory footprint while maintaining performance.
  arXiv  Detail & Related papers  (2021-02-24T19:55:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.