Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storage

• URL: http://arxiv.org/abs/2603.14583v1
• Date: Sun, 15 Mar 2026 20:02:05 GMT
• Title: Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storage
• Abstract summary: We propose a fundamentally different design approach: using lightweight and practical machine learning (ML) methods.<n>We present three ML-guided architectural policies: Pythia, Hermes, and Sibyl.<n>Our evaluation shows that Pythia, Hermes, and Sibyl significantly outperform the best-prior human-designed policies.
• Score: 7.728870871690254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the data-rich environment in which memory systems of modern computing platforms operate, many state-of-the-art architectural policies employed in the memory system rely on static, human-designed heuristics that fail to truly adapt to the workload and system behavior via principled learning methodologies. In this article, we propose a fundamentally different design approach: using lightweight and practical machine learning (ML) methods to enable adaptive, data-driven control throughout the memory hierarchy. We present three ML-guided architectural policies: (1) Pythia, a reinforcement learning-based data prefetcher for on-chip caches, (2) Hermes, a perceptron learning-based off-chip predictor for multi-level cache hierarchies, and (3) Sibyl, a reinforcement learning-based data placement policy for hybrid storage systems. Our evaluation shows that Pythia, Hermes, and Sibyl significantly outperform the best-prior human-designed policies, while incurring modest hardware overheads. Collectively, this article demonstrates that integrating adaptive learning into memory subsystems can lead to intelligent, self-optimizing architectures that unlock performance and efficiency gains beyond what is possible with traditional human-designed approaches.

Related papers

• ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems [16.145441371225637]
  We propose ConMem, a relation-aware and training-free framework for multi-agent adaptation.<n>Specifically, ConMem distills historical interaction trajectories into structured memory cards.<n>At runtime, ConMem retrieves cards according to task needs and coordinates them through the card graph to resolve strategy conflicts.
  arXiv  Detail & Related papers  (2026-06-07T15:59:15Z)
• Mitigating the Memory Bottleneck with Machine Learning-Driven and Data-Aware Microarchitectural Techniques [0.5701997979067353]
  dissertation shows that modern processors observe large amounts of application and system data during execution.<n>We demonstrate that such data-agnostic design leads to substantial missed opportunities for improving performance and energy efficiency.<n>We propose mechanisms that learn policies from observed execution behavior and exploit semantic characteristics of application data.
  arXiv  Detail & Related papers  (2026-03-08T15:34:25Z)
• RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design [77.30163153176954]
  RMBench is a simulation benchmark comprising 9 manipulation tasks that span multiple levels of memory complexity.<n>Mem-0 is a modular manipulation policy with explicit memory components designed to support controlled ablation studies.<n>We identify memory-related limitations in existing policies and provide empirical insights into how architectural design choices influence memory performance.
  arXiv  Detail & Related papers  (2026-03-01T18:59:59Z)
• Learning to Continually Learn via Meta-learning Agentic Memory Designs [22.10429892509733]
  ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace hand-engineered memory designs.<n>Our approach employs a Meta Agent that searches over memory designs expressed as executable code in an open-ended manner.
  arXiv  Detail & Related papers  (2026-02-08T01:20:49Z)
• The AI Hippocampus: How Far are We From Human Memory? [77.04745635827278]
  Implicit memory refers to the knowledge embedded within the internal parameters of pre-trained transformers.<n>Explicit memory involves external storage and retrieval components designed to augment model outputs with dynamic, queryable knowledge representations.<n>Agentic memory introduces persistent, temporally extended memory structures within autonomous agents.
  arXiv  Detail & Related papers  (2026-01-14T03:24:08Z)
• MemEvolve: Meta-Evolution of Agent Memory Systems [66.09735157017558]
  Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents.<n>MemeEvolve is a meta-evolutionary framework that jointly evolves agents' experiential knowledge and their memory architecture.<n> EvolveLab is a unified self-evolving memory that distills twelve representative memory systems into a modular design space.
  arXiv  Detail & Related papers  (2025-12-21T14:26:14Z)
• Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning [58.533203990515034]
  Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL)<n>We show that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements.<n>We finally distill these insights into Module-Specific Training (MST), a practical framework that exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.
  arXiv  Detail & Related papers  (2025-10-14T03:03:08Z)
• CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension [55.29309306566238]
  Current Large Language Models (LLMs) are confronted with overwhelming information volume when comprehending long-form documents.<n>This challenge raises the imperative of a cohesive memory module, which can elevate vanilla LLMs into autonomous reading agents.<n>We draw inspiration from Jean Piaget's Constructivist Theory, illuminating three traits of the agentic memory -- structured schemata, flexible assimilation, and dynamic accommodation.
  arXiv  Detail & Related papers  (2025-10-07T02:16:30Z)
• MemoryKT: An Integrative Memory-and-Forgetting Method for Knowledge Tracing [7.096160553754792]
  Simulating students' memory states is a promising approach to enhance both the performance and interpretability of knowledge tracing models.<n>Memory consists of three fundamental processes: encoding, storage, and retrieval.<n>This paper proposes memoryKT, a knowledge tracing model based on a novel temporal variational autoencoder.
  arXiv  Detail & Related papers  (2025-08-11T15:59:59Z)
• MemOS: A Memory OS for AI System [116.87568350346537]
  Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI)<n>Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.<n>MemOS is a memory operating system that treats memory as a manageable system resource.
  arXiv  Detail & Related papers  (2025-07-04T17:21:46Z)
• Improving Performance in Continual Learning Tasks using Bio-Inspired Architectures [4.2903672492917755]
  We develop a biologically inspired lightweight neural network architecture that incorporates synaptic plasticity mechanisms and neuromodulation. Our approach leads to superior online continual learning performance on Split-MNIST, Split-CIFAR-10, and Split-CIFAR-100 datasets. We further demonstrate the effectiveness of our approach by integrating key design concepts into other backpropagation-based continual learning algorithms.
  arXiv  Detail & Related papers  (2023-08-08T19:12:52Z)
• Neuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning [4.2903672492917755]
  We develop a biologically-inspired light weight neural network architecture that incorporates local learning and neuromodulation. We demonstrate the efficacy of our approach on both single task and continual learning setting.
  arXiv  Detail & Related papers  (2020-07-16T07:41:23Z)

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.