Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

• URL: http://arxiv.org/abs/2601.01280v2
• Date: Wed, 07 Jan 2026 18:16:54 GMT
• Title: Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory
• Abstract summary: We present an experimental, system-oriented analysis of long-term dialog memory architectures.<n>We introduce a unified framework that decomposes dialog memory systems into core components and supports both graph-based and non-graph approaches.
• Score: 11.649831360197531
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph structures are increasingly used in dialog memory systems, but empirical findings on their effectiveness remain inconsistent, making it unclear which design choices truly matter. We present an experimental, system-oriented analysis of long-term dialog memory architectures. We introduce a unified framework that decomposes dialog memory systems into core components and supports both graph-based and non-graph approaches. Under this framework, we conduct controlled, stage-wise experiments on LongMemEval and HaluMem, comparing common design choices in memory representation, organization, maintenance, and retrieval. Our results show that many performance differences are driven by foundational system settings rather than specific architectural innovations. Based on these findings, we identify stable and reliable strong baselines for future dialog memory research.

Related papers

• UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory [32.625416782173204]
  We introduce UtilMem, a diagnostic benchmark to evaluate memory utilization.<n>We find that strong performance on conventional factual-memory benchmarks does not reliably translate into effective memory utilization.<n>These findings expose a substantial gap between accessing stored information and using it effectively, and suggest that progress in long-term conversational memory will require architectures that explicitly support evidence integration and robustness to retrieval interference.
  arXiv  Detail & Related papers  (2026-08-31T09:41:26Z)
• GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory [87.58855368314693]
  We propose GraphMemix, a graph memory framework that models memory organization as query-aware evidence-forest construction.<n> Experimental results across four long-term multimodal memory benchmarks demonstrate significant improvements with different foundation models.
  arXiv  Detail & Related papers  (2026-08-27T11:28:49Z)
• Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization [22.756681935673658]
  We formalize streaming dialogue summarization, where a system must summarize a current window using selective memory from an unbounded history under a fixed budget.<n>We propose ReMEMBER, a missing-evidence memory framework that conditions retrieval on unresolved window dependencies and refines retrieved chunks into evidence-dense memory under a fixed budget.
  arXiv  Detail & Related papers  (2026-08-10T02:48:37Z)
• Memory Shot for Long-Term Dialogue [27.934717347947352]
  We propose MemShot, which renders local contiguous dialogue spans into structured visual memory units.<n>MemShot achieves stable and competitive performance on both LoCoMo and LongMemEval.<n>Further analysis reveals that MemShot enhances the localization and utilization of historical evidence.
  arXiv  Detail & Related papers  (2026-05-30T01:59:52Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• 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)
• Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations [6.566696478685466]
  Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions.<n>Existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models.<n>This survey presents a structured analysis of agentic memory from both architectural and system perspectives.
  arXiv  Detail & Related papers  (2026-02-22T19:50:01Z)
• TraceMem: Weaving Narrative Memory Schemata from User Conversational Traces [9.654990538033362]
  Sustaining long-term interactions remains a bottleneck for Large Language Models.<n>We propose TraceMem, a framework that weaves structured, narrative memory schemata from user conversational traces.<n>TraceMem achieves state-of-the-art performance with a brain-inspired architecture.
  arXiv  Detail & Related papers  (2026-02-10T12:14:58Z)
• 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)
• 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)
• Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management [63.48041801851891]
  Fine-Mem is a unified framework designed for fine-grained feedback alignment.<n> Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-01-13T11:06:17Z)
• HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents [3.9396865837159822]
  HiMem is a hierarchical long-term memory framework for long-horizon dialogues.<n>It supports memory construction, retrieval, and dynamic updating during sustained interactions.<n>Results show HiMem consistently outperforms representative baselines in accuracy, consistency, and long-term reasoning.
  arXiv  Detail & Related papers  (2026-01-10T01:26:01Z)
• 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)
• EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning [42.339841548168565]
  Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extended interactions.<n>We introduce EverMemOS, a self-organizing memory operating system that implements an engram-inspired lifecycle for computational memory.<n>EverMemOS achieves state-of-the-art performance on memory-augmented reasoning tasks.
  arXiv  Detail & Related papers  (2026-01-05T14:39:43Z)
• Memory in the Age of AI Agents [217.9368190980982]
  This work aims to provide an up-to-date landscape of current agent memory research.<n>We identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory.<n>To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks.
  arXiv  Detail & Related papers  (2025-12-15T17:22:34Z)
• 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)
• Cognitively-Inspired Episodic Memory Architectures for Accurate and Efficient Character AI [1.0742675209112622]
  Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off.<n>We present an architecture that resolves this tension through offline data augmentation and efficient parallel retrieval from structured episodic memory.<n>Our system transforms biographical data into 1,774 enriched first-person memories with affective-semantic metadata, then employs two-stage retrieval achieving 0.52s prompt generation.
  arXiv  Detail & Related papers  (2025-11-01T02:26:16Z)
• Evaluating Long-Term Memory for Long-Context Question Answering [100.1267054069757]
  We present a systematic evaluation of memory-augmented methods using LoCoMo, a benchmark of synthetic long-context dialogues annotated for question-answering tasks.<n>Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-27T18:03:50Z)
• Structured Memory Mechanisms for Stable Context Representation in Large Language Models [16.929937978584917]
  The model integrates explicit memory units, gated writing mechanisms, and attention-based reading modules.<n>A forgetting function is introduced to enable dynamic updates of memory content.<n>The model achieves clear advantages in text generation consistency, stability in multi-turn question answering, and accuracy in cross-context reasoning.
  arXiv  Detail & Related papers  (2025-05-28T22:49:04Z)
• 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)
• SCM: Enhancing Large Language Model with Self-Controlled Memory Framework [54.33686574304374]
  Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.<n>We propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information.
  arXiv  Detail & Related papers  (2023-04-26T07:25:31Z)
• Ranking Enhanced Dialogue Generation [77.8321855074999]
  How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation. Previous works usually employ various neural network architectures to model the history. This paper proposes a Ranking Enhanced Dialogue generation framework.
  arXiv  Detail & Related papers  (2020-08-13T01:49:56Z)
• ORD: Object Relationship Discovery for Visual Dialogue Generation [60.471670447176656]
  We propose an object relationship discovery (ORD) framework to preserve the object interactions for visual dialogue generation. A hierarchical graph convolutional network (HierGCN) is proposed to retain the object nodes and neighbour relationships locally, and then refines the object-object connections globally. Experiments have proved that the proposed method can significantly improve the quality of dialogue by utilising the contextual information of visual relationships.
  arXiv  Detail & Related papers  (2020-06-15T12:25:40Z)

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.