Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models

• URL: http://arxiv.org/abs/2601.03417v1
• Date: Tue, 06 Jan 2026 21:10:10 GMT
• Title: Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models
• Authors: Xin Zhang, Kailai Yang, Hao Li, Chenyue Li, Qiyu Wei, Sophia Ananiadou,
• Abstract summary: We propose LatentGraphMem, a memory framework that combines implicit graph memory with explicit subgraph retrieval.<n>LatentGraphMem stores a graph-structured memory in latent space for stability and efficiency.<n> Experiments on long-horizon benchmarks across multiple model scales show that LatentGraphMem consistently outperforms representative explicit-graph and latent-memory baselines.
• Score: 26.694294747866834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing memory systems largely follow two paradigms: explicit structured memories offer interpretability but often become brittle under long-context overload, while latent memory mechanisms are efficient and stable yet difficult to inspect. We propose LatentGraphMem, a memory framework that combines implicit graph memory with explicit subgraph retrieval. LatentGraphMem stores a graph-structured memory in latent space for stability and efficiency, and exposes a task-specific subgraph retrieval interface that returns a compact symbolic subgraph under a fixed budget for downstream reasoning and human inspection. During training, an explicit graph view is materialized to interface with a frozen reasoner for question-answering supervision. At inference time, retrieval is performed in latent space and only the retrieved subgraph is externalized. Experiments on long-horizon benchmarks across multiple model scales show that LatentGraphMem consistently outperforms representative explicit-graph and latent-memory baselines, while enabling parameter-efficient adaptation and flexible scaling to larger reasoners without introducing large symbolic artifacts.

Related papers

• VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph [42.348770377488094]
  VimRAG is a framework tailored for multimodal Retrieval-augmented Reasoning across text, images, and videos.<n>We propose a Graph-Guided Policy Optimization strategy to disentangle step-wise validity from trajectory-level rewards.<n>Experiments demonstrate that VimRAG consistently achieves state-of-the-art performance on diverse multimodal RAG benchmarks.
  arXiv  Detail & Related papers  (2026-02-13T09:05:09Z)
• Graph-based Agent Memory: Taxonomy, Techniques, and Applications [63.70340159016138]
  Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks.<n>Among diverse paradigms, graph stands out as a powerful structure for agent memory due to the intrinsic capabilities to model relational dependencies.<n>This survey presents a comprehensive review of agent memory from the graph-based perspective.
  arXiv  Detail & Related papers  (2026-02-05T13:49:05Z)
• Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning [55.251697395358285]
  Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments.<n>To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism that can retain, organize, and retrieve past experiences.<n>We propose CompassMem, an event-centric memory framework inspired by Event Theory.
  arXiv  Detail & Related papers  (2026-01-08T08:44:07Z)
• MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents [4.4848347718892425]
  Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning.<n>Existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information.<n>We propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across semantic, temporal, causal, and entity graphs.
  arXiv  Detail & Related papers  (2026-01-06T18:29:43Z)
• LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning [15.189701702660821]
  LiCoMemory is an end-to-end agentic memory framework for real-time updating and retrieval.<n>CoGraph is a lightweight hierarchical graph that utilizes entities and relations as semantic indexing layers.<n>Experiments on long-term dialogue benchmarks, LoCoMo and LongMemEval, show that LiCoMemory not only outperforms established baselines in temporal reasoning, multi-session consistency, and retrieval efficiency, but also notably reduces update latency.
  arXiv  Detail & Related papers  (2025-11-03T11:02:40Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)
• TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG [3.3593672127922836]
  TOBUGraph is a graph-based retrieval framework that first constructs the knowledge graph from unstructured data.<n>It extracts structured knowledge and diverse relationships among data, going beyond RAG's text-to-text similarity.<n>We demonstrate TOBUGraph's effectiveness in TOBU, a real-world application in production for personal memory organization and retrieval.
  arXiv  Detail & Related papers  (2024-12-06T22:05:39Z)
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks [63.35819388164267]
  We present a framework to tackle the memory explosion problem using memory replay techniques. PDGNNs with Topology-aware Embedding Memory (TEM) significantly outperform state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-01-24T03:03:17Z)
• LaMemo: Language Modeling with Look-Ahead Memory [50.6248714811912]
  We propose Look-Ahead Memory (LaMemo) that enhances the recurrence memory by incrementally attending to the right-side tokens. LaMemo embraces bi-directional attention and segment recurrence with an additional overhead only linearly proportional to the memory length. Experiments on widely used language modeling benchmarks demonstrate its superiority over the baselines equipped with different types of memory.
  arXiv  Detail & Related papers  (2022-04-15T06:11:25Z)
• GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings [51.82434518719011]
  GNNAutoScale (GAS) is a framework for scaling arbitrary message-passing GNNs to large graphs. Gas prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations. Gas reaches state-of-the-art performance on large-scale graphs.
  arXiv  Detail & Related papers  (2021-06-10T09:26:56Z)
• Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks [65.3963282551994]
  We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time. We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy.
  arXiv  Detail & Related papers  (2020-10-06T15:16:31Z)
• Video Object Segmentation with Episodic Graph Memory Networks [198.74780033475724]
  A graph memory network is developed to address the novel idea of "learning to update the segmentation model" We exploit an episodic memory network, organized as a fully connected graph, to store frames as nodes and capture cross-frame correlations by edges. The proposed graph memory network yields a neat yet principled framework, which can generalize well both one-shot and zero-shot video object segmentation tasks.
  arXiv  Detail & Related papers  (2020-07-14T13:19:19Z)

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.