HEMA : A Hippocampus-Inspired Extended Memory Architecture for Long-Context AI Conversations

• URL: http://arxiv.org/abs/2504.16754v1
• Date: Wed, 23 Apr 2025 14:27:12 GMT
• Title: HEMA : A Hippocampus-Inspired Extended Memory Architecture for Long-Context AI Conversations
• Abstract summary: Large language models (LLMs) struggle with maintaining coherence in extended conversations spanning hundreds of turns.<n>This paper introduces HEMA, a dual-memory system inspired by human cognitive processes.<n>With 10K indexed chunks, Vector Memory achieves P@5 >= 0.80 and R@50 >= 0.74, doubling the area under the precision-recall curve.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) struggle with maintaining coherence in extended conversations spanning hundreds of turns, despite performing well within their context windows. This paper introduces HEMA (Hippocampus-Inspired Extended Memory Architecture), a dual-memory system inspired by human cognitive processes. HEMA combines Compact Memory - a continuously updated one-sentence summary preserving global narrative coherence, and Vector Memory - an episodic store of chunk embeddings queried via cosine similarity. When integrated with a 6B-parameter transformer, HEMA maintains coherent dialogues beyond 300 turns while keeping prompt length under 3,500 tokens. Experimental results show substantial improvements: factual recall accuracy increases from 41% to 87%, and human-rated coherence improves from 2.7 to 4.3 on a 5-point scale. With 10K indexed chunks, Vector Memory achieves P@5 >= 0.80 and R@50 >= 0.74, doubling the area under the precision-recall curve compared to summarization-only approaches. Ablation studies reveal two key insights: semantic forgetting through age-weighted pruning reduces retrieval latency by 34% with minimal recall loss, and a two-level summary hierarchy prevents cascade errors in ultra-long conversations exceeding 1,000 turns. HEMA demonstrates that combining verbatim recall with semantic continuity provides a practical solution for privacy-aware conversational AI capable of month-long dialogues without model retraining.

Related papers

• Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers [0.0]
  Vision Transformers provide strong visual representations but typically rely on slowly updated parameters.<n>This work proposes textitHierarchical Hebbian Memory, a three-level memory architecture composed of rapid Working Memory, persistent Routed Episodic Memory, and slower Semantic Memory.
  arXiv  Detail & Related papers  (2026-08-31T20:51:51Z)
• VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction [92.2925193726566]
  VoiceMem is a memory architecture with a parallel informational left brain, an emotional right brain, and streaming memory I/O mechanisms.<n>Experiments and real-world deployment show three advantages.
  arXiv  Detail & Related papers  (2026-08-26T16:50:05Z)
• Echo-Memory: A Controlled Study of Memory in Action World Models [58.77172260403133]
  We present a controlled study of memory mechanisms in action-conditioned world models.<n>Existing memory designs are hard to compare because gains are entangled with backbone, training, retrieval, and evaluation differences.<n>We use Echo-Memory to fix the action-to-video interface and varies only how history is stored and read by the generator.
  arXiv  Detail & Related papers  (2026-06-08T17:54:10Z)
• Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation [89.70897512515477]
  Action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual response.<n>Maintaining visual fidelity and 3D consistency over long autoregressive rollouts remains challenging.<n>Existing 3D-aware methods often suffer from catastrophic drift due to two impediments: information loss from textitLatent--RGB Cycling, and the training--inference gap induced by the textiterror-free hypothesis.<n>We present textbfRobust Dreamer, a memory-augmented framework built around how to
  arXiv  Detail & Related papers  (2026-05-29T05:21:33Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency [2.447989276487424]
  Large language models often suffer from fact loss, timeline confusion, persona drift, and reduced stability during long-range interaction.<n>We introduce ARPM, an external temporal memory governance framework for long-term dialogue.<n>We show that ARPM treats continuity as a traceable, auditable, and transferable governance problem.
  arXiv  Detail & Related papers  (2026-05-14T13:12:49Z)
• EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval [0.0]
  EngramaBench is a benchmark for long-term conversational memory built around five personas, one hundred multi-session conversations, and one hundred fifty queries.<n>We evaluate Engrama, a graph-structured memory system, against GPT-4o full-context prompting and Mem0, an open-source vector-retrieval memory system.
  arXiv  Detail & Related papers  (2026-04-23T02:51:42Z)
• MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents [2.541923091180284]
  Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning.<n>We present MemMachine, an open-source memory system that integrates short-term, long-term episodic, and profile memory.<n>MemMachine uses contextualized retrieval that expands nucleus matches with surrounding context, improving recall when relevant evidence spans multiple dialogue turns.
  arXiv  Detail & Related papers  (2026-04-06T16:57:06Z)
• SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems [0.0]
  We present SuperLocalMemory V3.3 ("The Living Brain"), a local-first agent memory system.<n>It implements the full cognitive memory taxonomy with mathematical lifecycle dynamics.<n>It is open source under the Elastic License 2.0, runs entirely on CPU, and has over 5,000 monthly downloads.
  arXiv  Detail & Related papers  (2026-04-06T08:27:26Z)
• From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents [78.30630000529133]
  We propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory.<n> MM-Mem memory structures hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic.<n>Experiments confirm the effectiveness of MM-Mem on both offline and streaming tasks.
  arXiv  Detail & Related papers  (2026-03-02T05:12:45Z)
• Mind the Gap: Why Neural Memory Fails Under Semantic Density [0.0]
  Current AI systems lack this separation, attempting both functions through neural weights alone.<n>We identify the 'Stability Gap' in online neural memory.<n>We show collapse occurs with as few as N=5 facts at high density.<n>We also identify schema drift and version ambiguity as primary failure modes in production systems.
  arXiv  Detail & Related papers  (2026-01-14T18:55:23Z)
• 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)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• 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)
• Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation [8.14424628742372]
  Vision-and-Language Navigation (VLN) requires agents to follow natural language instructions through environments.<n>Existing approaches for memory-persistent VLN face critical limitations.<n>We present Memoir, which employs imagination as a retrieval mechanism grounded by explicit memory.
  arXiv  Detail & Related papers  (2025-10-09T17:58:01Z)
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation [59.31354761628506]
  Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it.<n>We propose MemoryVLA, a Cognition-Memory-Action framework for long-horizon robotic manipulation.<n>We evaluate it on 150+ simulation and real-world tasks across three robots.
  arXiv  Detail & Related papers  (2025-08-26T17:57:16Z)
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents [84.62985963113245]
  We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks.<n>At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning.<n>We show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task.
  arXiv  Detail & Related papers  (2025-06-18T19:44:46Z)
• MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs [0.0]
  Human intelligence relies on inner monologue to process complex information.<n>We introduce MIRROR, a cognitive architecture that implements parallel reasoning capabilities in large language models.<n>LLMs utilizing the MIRROR architecture achieve up to 156% relative improvement in critical safety scenarios.
  arXiv  Detail & Related papers  (2025-05-31T07:17:48Z)
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory [0.5584627289325719]
  Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses. But their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues. We introduce Mem0, a scalable memory-centric architecture that addresses this issue by dynamically extracting, consolidating, and retrieving salient information from ongoing conversations.
  arXiv  Detail & Related papers  (2025-04-28T01:46:35Z)
• In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents [70.12342024019044]
  Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information limits their effectiveness.<n>We propose Reflective Memory Management (RMM), a novel mechanism for long-term dialogue agents, integrating forward- and backward-looking reflections.<n>RMM shows more than 10% accuracy improvement over the baseline without memory management on the LongMemEval dataset.
  arXiv  Detail & Related papers  (2025-03-11T04:15:52Z)
• LightThinker: Thinking Step-by-Step Compression [53.8069487638972]
  We propose LightThinker, a method that enables large language models to dynamically compress intermediate thoughts during reasoning.<n>Inspired by human cognitive processes, LightThinker compresses thought steps into compact representations and discards the original reasoning chains.<n>Experiments show that LightThinker reduces peak memory usage and inference time, while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-02-21T16:57:22Z)
• MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation [15.64077949677469]
  We present a novel Memory-Augmented Dialogue Benchmark (MADail-Bench) to evaluate the effectiveness of memory-augmented dialogue systems (MADS) The benchmark assesses two tasks separately: memory retrieval and memory recognition with the incorporation of both passive and proactive memory recall data. Results from cutting-edge embedding models and large language models on this benchmark indicate the potential for further advancement.
  arXiv  Detail & Related papers  (2024-09-23T17:38:41Z)
• KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems [12.461941212597877]
  Embodied AI agents often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. We introduce KARMA, an innovative memory system that integrates long-term and short-term memory modules. Our memory-augmented embodied AI agent improves success rates by 1.3x and 2.3x in Composite Tasks and Complex Tasks.
  arXiv  Detail & Related papers  (2024-09-23T11:02:46Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing [33.720656946186885]
  Hierarchical Memory Transformer (HMT) is a novel framework that facilitates a model's long-context processing ability. HMT consistently improves the long-context processing ability of existing models.
  arXiv  Detail & Related papers  (2024-05-09T19:32:49Z)
• StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses [67.92595110412094]
  StreamingDialogue compresses long dialogue history into conv-attn sinks with minimal losses. Our method outperforms strong baselines in dialogue tasks.
  arXiv  Detail & Related papers  (2024-03-13T07:44:14Z)
• Ever-Evolving Memory by Blending and Refining the Past [30.63352929849842]
  CREEM is a novel memory system for long-term conversation. It seamlessly connects past and present information, while also possessing the ability to forget obstructive information.
  arXiv  Detail & Related papers  (2024-03-03T08:12:59Z)
• Simple linear attention language models balance the recall-throughput tradeoff [60.06020449520365]
  We propose BASED, a simple architecture combining linear and sliding window attention.<n>We train language models up to 1.3b parameters and show that BASED matches the strongest sub-quadratic models in perplexity and outperforms them on real-world recall-intensive tasks by 6.22 accuracy points.
  arXiv  Detail & Related papers  (2024-02-28T19:28:27Z)
• MemoryBank: Enhancing Large Language Models with Long-Term Memory [7.654404043517219]
  We propose MemoryBank, a novel memory mechanism tailored for Large Language Models. MemoryBank enables the models to summon relevant memories, continually evolve through continuous memory updates, comprehend, and adapt to a user personality by synthesizing information from past interactions.
  arXiv  Detail & Related papers  (2023-05-17T14:40:29Z)
• Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition [66.47000813920619]
  We propose a non-autoregressive end-to-end speech recognition system called LASO. Because of the non-autoregressive property, LASO predicts a textual token in the sequence without the dependence on other tokens. We conduct experiments on publicly available Chinese dataset AISHELL-1.
  arXiv  Detail & Related papers  (2020-05-11T04:45:02Z)

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.