Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction

• URL: http://arxiv.org/abs/2603.29023v1
• Date: Mon, 30 Mar 2026 21:35:28 GMT
• Title: Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction
• Abstract summary: Large language models lack persistent, structured memory for long-term interaction and context-sensitive retrieval.<n>We propose a bio-inspired memory framework grounded in complementary learning systems theory, cognitive behavioral therapy's belief hierarchy, dual-process cognition, and fuzzy-trace theory.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models lack persistent, structured memory for long-term interaction and context-sensitive retrieval. Expanding context windows does not solve this: recent evidence shows that context length alone degrades reasoning by up to 85% - even with perfect retrieval. We propose a bio-inspired memory framework grounded in complementary learning systems theory, cognitive behavioral therapy's belief hierarchy, dual-process cognition, and fuzzy-trace theory, organized around three principles: (1) Memory has valence, not just content - pre-computed emotional-associative summaries (valence vectors) organized in an emergent belief hierarchy inspired by Beck's cognitive model enable instant orientation before deliberation; (2) Retrieval defaults to System 1 with System 2 escalation - automatic spreading activation and passive priming as default, with deliberate retrieval only when needed, and graded epistemic states that address hallucination structurally; and (3) Encoding is active, present, and feedback-dependent - a thalamic gateway tags and routes information between stores, while the executive forms gists through curiosity-driven investigation, not passive exposure. Seven functional properties specify what any implementation must satisfy. Over time, the system converges toward System 1 processing - the computational analog of clinical expertise - producing interactions that become cheaper, not more expensive, with experience.

Related papers

• Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis [77.02066500576528]
  Process-aware Language Cognitive Diagnosis (PLCD) framework uses language-derived structures as cognitive priors and response records to calibrate student posterior states.<n>PLCD not only outperforms traditional baselines in predicting student performance but also exhibits strong cognitive transfer capabilities.
  arXiv  Detail & Related papers  (2026-09-11T03:51:20Z)
• Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data [8.564332409420473]
  We propose Setoka, a benchmark for evaluating memory-augmented personalized agents.<n>Setoka defines four levels of user understanding, i.e., semantic memory, episodic memory, behavior pattern, and personality trait.<n>Our comprehensive evaluation reveals that while existing systems perform well on semantic memory retrieval, their performance declines on episodic memory.
  arXiv  Detail & Related papers  (2026-07-29T15:47:40Z)
• Navigating the Emotion Tree: Hierarchical Hyperbolic RAG for Multimodal Emotion Recognition [56.650820426231284]
  Multimodal emotion recognition aims to integrate text, audio, and video sources to understand human affective states.<n>Although large language models excel at multimodal reasoning, they typically treat emotion categories as independent labels.<n>We propose bftextHyperEmo-RAG, a retrieval-augmented generation framework that leverages a structured emotional knowledge base.
  arXiv  Detail & Related papers  (2026-05-16T10:04:48Z)
• Cognifold: Always-On Proactive Memory via Cognitive Folding [15.403868103736556]
  CogniFold is a brain-inspired "always-on" agent memory designed for the next generation of proactive assistants.<n>We ground this by extending Complementary Learning Systems theory from two layers (hippocampus, neocortex) to three, adding a prefrontal intent layer.<n>We evaluate structural formation using CogEval-Bench, demonstrating that CogniFold uniquely produces memory structures that match cognitive expectations.
  arXiv  Detail & Related papers  (2026-05-13T12:34:39Z)
• HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents [8.86975756125001]
  HeLa-Mem is a bio-inspired memory architecture that models memory as a dynamic graph with Hebbian learning dynamics.<n>HeLa-Mem employs a dual-level organization: (1) an episodic memory graph that evolves through co-activation patterns, and (2) a semantic memory store populated via Hebbian Distillation.<n> Experiments on LoCoMo demonstrate superior performance across four question categories while using significantly fewer context tokens.
  arXiv  Detail & Related papers  (2026-04-18T05:11:18Z)
• 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)
• Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory [7.934989469945716]
  NS-Mem is a long-term neuro-symbolic memory framework designed to advance multimodal agent reasoning.<n> Experiments on real-world multimodal reasoning benchmarks demonstrate that Neural-Symbolic Memory achieves an average 4.35% improvement in overall reasoning accuracy.
  arXiv  Detail & Related papers  (2026-03-16T13:43:22Z)
• Memory-guided Prototypical Co-occurrence Learning for Mixed Emotion Recognition [56.00118641432005]
  We propose a Memory-guided Prototypical Co-occurrence Learning framework that explicitly models emotion co-occurrence patterns.<n>Inspired by human cognitive memory systems, we introduce a memory retrieval strategy to extract semantic-level co-occurrence associations.<n>Our model learns affectively informative representations for accurate emotion distribution prediction.
  arXiv  Detail & Related papers  (2026-02-24T04:11:25Z)
• 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)
• AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents [69.39123054975218]
  Memory serves as the pivotal nexus bridging past and future.<n>Recent research on autonomous agents has increasingly focused on designing efficient memory by drawing on cognitive neuroscience.
  arXiv  Detail & Related papers  (2025-12-29T10:01:32Z)
• 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)
• GENESIS: A Generative Model of Episodic-Semantic Interaction [0.40286876168661084]
  We introduce the Generative Episodic-Semantic Integration System (GENESIS)<n>GENESIS formalizes memory as the interaction between two limited-capacity generative systems.<n>It provides a principled account of memory as an active, constructive, and resource-bounded process.
  arXiv  Detail & Related papers  (2025-10-17T17:11:13Z)
• Consciousness is entailed by compositional learning of new causal structures in deep predictive processing systems [0.0]
  In humans, such learning includes specific declarative memory formation and is closely associated with consciousness. We extend predictive processing by adding online, single-example new structure learning via hierarchical binding of unpredicted inferences. Our proposal naturally unifies the feature binding, recurrent processing, predictive processing, and global theories of consciousness.
  arXiv  Detail & Related papers  (2023-01-17T17:06:48Z)
• A Cognitive Architecture for Machine Consciousness and Artificial Superintelligence: Thought Is Structured by the Iterative Updating of Working Memory [0.0]
  This article provides an analytical framework for how to simulate human-like thought processes within a computer. It describes how attention and memory should be structured, updated, and utilized to search for associative additions to the stream of thought.
  arXiv  Detail & Related papers  (2022-03-29T22:28:30Z)
• Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning [49.6928533575956]
  We use neural inference to mediate between the neural System 1 and the logical System 2. Results in robust story generation and grounded instruction-following show that this approach can increase the coherence and accuracy of neurally-based generations.
  arXiv  Detail & Related papers  (2021-07-06T17:59:49Z)

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.