Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning

• URL: http://arxiv.org/abs/2504.06135v1
• Date: Tue, 08 Apr 2025 15:31:00 GMT
• Title: Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning
• Abstract summary: We present SHIMI (Semantic Hierarchical Memory Index), a unified architecture that models knowledge as a dynamically structured hierarchy of concepts.<n>SHIMI is designed for decentralized ecosystems, where agents maintain local memory trees and synchronize them asynchronously across networks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-Augmented Generation (RAG) and vector-based search have become foundational tools for memory in AI systems, yet they struggle with abstraction, scalability, and semantic precision - especially in decentralized environments. We present SHIMI (Semantic Hierarchical Memory Index), a unified architecture that models knowledge as a dynamically structured hierarchy of concepts, enabling agents to retrieve information based on meaning rather than surface similarity. SHIMI organizes memory into layered semantic nodes and supports top-down traversal from abstract intent to specific entities, offering more precise and explainable retrieval. Critically, SHIMI is natively designed for decentralized ecosystems, where agents maintain local memory trees and synchronize them asynchronously across networks. We introduce a lightweight sync protocol that leverages Merkle-DAG summaries, Bloom filters, and CRDT-style conflict resolution to enable partial synchronization with minimal overhead. Through benchmark experiments and use cases involving decentralized agent collaboration, we demonstrate SHIMI's advantages in retrieval accuracy, semantic fidelity, and scalability - positioning it as a core infrastructure layer for decentralized cognitive systems.

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)
• HyphaeDB: A Living Knowledge Topology for Agent-First Memory [0.0]
  We introduce HyphaeDB, an agent-native memory infrastructure for multi-agent AI systems.<n>In HyphaeDB, agents are nodes in the vector space with persistent positions, knowledge propagates via a gossip protocol.<n>We present the architecture built on three primitives, a multi-layer abstraction hierarchy, and theoretical analysis.
  arXiv  Detail & Related papers  (2026-06-27T07:15:41Z)
• Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings [10.299190830046872]
  We present a post-hoc framework to explain, verify, and align semantic hierarchies induced by a VLM over a given set of child classes.<n>We quantify plausibility by comparing the extracted tree against human retrieval using efficient tree-aware and edge-level consistency measures, and we evaluate utility via explainable hierarchical tree-traversal inference.
  arXiv  Detail & Related papers  (2026-03-26T00:38:38Z)
• Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence [13.062618208633483]
  This paper proposes AgentOS, a holistic conceptual framework that redefines the Large Language Models as a "Reasoning Kernel" governed by structured operating system logic.<n>By mapping classical OS abstractions such as memory paging interrupt handling and process scheduling onto LLM native constructs, this review provides a rigorous roadmap for architecting resilient scalable and self-evolving cognitive environments.
  arXiv  Detail & Related papers  (2026-02-24T14:12:21Z)
• Deep Global Clustering for Hyperspectral Image Segmentation: Concepts, Applications, and Open Challenges [1.9116784879310027]
  Hyperspectral imaging (HSI) analysis faces computational bottlenecks due to massive data volumes that exceed available memory.<n>This report presents Deep Global Clustering (DGC), a conceptual framework for memory-efficient HSI segmentation.<n>DGC operates on small patches with overlapping regions to enforce consistency, enabling training in under 30 minutes on consumer hardware.
  arXiv  Detail & Related papers  (2025-12-30T12:10:43Z)
• Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation [1.5329374712396715]
  This paper introduces OSM-L, a self-supervised distributed learning paradigm designed to uncover higher-level latent knowledge from distributed data.<n>OSM-L iteratively aligns local data representations, enabling information diffusion and convergence.<n> Experimental results confirm OSM-L's convergence and representation capabilities on structured datasets.
  arXiv  Detail & Related papers  (2025-12-28T22:25:16Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation [1.5223740593989445]
  Unsupervised Video Object (UVOS) aims to predict pixel-level masks for the most salient objects in videos without any prior annotations.<n>Our analysis reveals a simple but fundamental flaw in existing methods: over-reliance on memorizing high-level semantic features.<n>We propose a novel hierarchical memory architecture to incorporate both shallow- and high-level features for memory.
  arXiv  Detail & Related papers  (2025-07-30T08:11:18Z)
• Interpreting CLIP with Hierarchical Sparse Autoencoders [8.692675181549117]
  Matryoshka SAE (MSAE) learns hierarchical representations at multiple granularities simultaneously.<n>MSAE establishes a new state-of-the-art frontier between reconstruction quality and sparsity for CLIP.
  arXiv  Detail & Related papers  (2025-02-27T22:39:13Z)
• Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation [69.01029651113386]
  Embodied-RAG is a framework that enhances the model of an embodied agent with a non-parametric memory system.<n>At its core, Embodied-RAG's memory is structured as a semantic forest, storing language descriptions at varying levels of detail.<n>We demonstrate that Embodied-RAG effectively bridges RAG to the robotics domain, successfully handling over 250 explanation and navigation queries.
  arXiv  Detail & Related papers  (2024-09-26T21:44:11Z)
• Federated Contrastive Learning for Personalized Semantic Communication [55.46383524190467]
  We design a federated contrastive learning framework aimed at supporting personalized semantic communication. FedCL enables collaborative training of local semantic encoders across multiple clients and a global semantic decoder owned by the base station. To tackle the semantic imbalance issue arising from heterogeneous datasets across distributed clients, we employ contrastive learning to train a semantic centroid generator.
  arXiv  Detail & Related papers  (2024-06-13T14:45:35Z)
• Spatial Semantic Recurrent Mining for Referring Image Segmentation [63.34997546393106]
  We propose Stextsuperscript2RM to achieve high-quality cross-modality fusion. It follows a working strategy of trilogy: distributing language feature, spatial semantic recurrent coparsing, and parsed-semantic balancing. Our proposed method performs favorably against other state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-05-15T00:17:48Z)
• DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks [64.62314068155997]
  We present textitDecentralized Embedding Framework for Heterogeneous Information Network (DeHIN) in this paper. DeHIN presents a context preserving partition mechanism that innovatively formulates a large HIN as a hypergraph. Our framework then adopts a decentralized strategy to efficiently partition HINs by adopting a tree-like pipeline.
  arXiv  Detail & Related papers  (2022-01-08T04:08:36Z)
• Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images [28.560068780733342]
  A novel context aggregation network (CATNet) is proposed to improve the feature extraction process. The proposed model exploits three lightweight plug-and-play modules, namely dense feature pyramid network (DenseFPN), spatial context pyramid ( SCP), and hierarchical region of interest extractor (HRoIE)
  arXiv  Detail & Related papers  (2021-11-22T08:55:25Z)
• Deep Fusion Clustering Network [38.540761683389135]
  We propose a Deep Fusion Clustering Network (DFCN) for deep clustering. In our network, an interdependency learning-based Structure and Attribute Information Fusion (SAIF) module is proposed to explicitly merge the representations learned by an autoencoder and a graph autoencoder. Experiments on six benchmark datasets have demonstrated that the proposed DFCN consistently outperforms the state-of-the-art deep clustering methods.
  arXiv  Detail & Related papers  (2020-12-15T09:37:59Z)
• Adaptive Linear Span Network for Object Skeleton Detection [56.78705071830965]
  We propose adaptive linear span network (AdaLSN) to automatically configure and integrate scale-aware features for object skeleton detection. AdaLSN substantiates its versatility by achieving significantly higher accuracy and latency trade-off. It also demonstrates general applicability to image-to-mask tasks such as edge detection and road extraction.
  arXiv  Detail & Related papers  (2020-11-08T12:51:14Z)
• Deep Autoencoding Topic Model with Scalable Hybrid Bayesian Inference [55.35176938713946]
  We develop deep autoencoding topic model (DATM) that uses a hierarchy of gamma distributions to construct its multi-stochastic-layer generative network. We propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a downward generative model. The efficacy and scalability of our models are demonstrated on both unsupervised and supervised learning tasks on big corpora.
  arXiv  Detail & Related papers  (2020-06-15T22:22:56Z)

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.