Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention

• URL: http://arxiv.org/abs/2603.29194v1
• Date: Tue, 31 Mar 2026 02:58:26 GMT
• Title: Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention
• Abstract summary: Long-horizon dialogue systems suffer from semanticdrift and unstable memory retention across extended sessions.<n>This paper presents a Multi-Layer Memory Framework that decomposes dialogue history into working, episodic, and semantic layers with adaptive retrieval gating and retention regularization.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-horizon dialogue systems suffer from semanticdrift and unstable memory retention across extended sessions. This paper presents a Multi-Layer Memory Framework that decomposes dialogue history into working, episodic, and semantic layers with adaptive retrieval gating and retention regularization. The architecture controls cross-session drift while maintaining bounded context growth and computational efficiency. Experiments on LOCOMO, LOCCO, and LoCoMo show improved performance, achieving 46.85 Success Rate, 0.618 overall F1 with 0.594 multi-hop F1, and 56.90% six-period retention while reducing false memory rate to 5.1% and context usage to 58.40%. Results confirm enhanced long-term retention and reasoning stability under constrained context budgets.

Related papers

• FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue [9.111886840996501]
  We propose FTA-Mem, a structured memory framework for low-density long-term dialogue.<n>FTA-Mem uses Boundary-preserving Window (BWS) to form coherent situation fragments, and constructs Fact-Time-Affect Memory Units.<n>Experiments on ES-MemEval and LoCoMo show that FTA-Mem improves overall long-term memory question answering across benchmarks with different information-density characteristics.
  arXiv  Detail & Related papers  (2026-08-17T09:14:31Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• 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)
• 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)
• Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency [0.0]
  Long-horizon conversational agents require persistent memory for coherent reasoning.<n> uncontrolled accumulation causes temporal decay and false memory propagation.<n>This work introduces an adaptive budgeted forgetting framework that regulates memory through relevanceguided scoring and bounded optimization.
  arXiv  Detail & Related papers  (2026-04-02T17:14:53Z)
• 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)
• TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents [31.793564520129348]
  We present TiMem, a temporal-hierarchical memory framework that organizes conversations through a Temporal Memory Tree (TMT)<n>TiMem is characterized by three core properties: (1) temporal--hierarchical organization through TMT; (2) semantic-guided consolidation that enables memory integration across hierarchical levels without fine-tuning; and (3) complexity-aware memory recall that balances and efficiency across queries of varying complexity.
  arXiv  Detail & Related papers  (2026-01-06T09:24:19Z)
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
  Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
  arXiv  Detail & Related papers  (2026-01-05T08:24:16Z)
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents [80.33280979339123]
  We introduce Memory-T1, a framework that learns a time-aware memory selection policy using reinforcement learning (RL)<n>On the Time-Dialog benchmark, Memory-T1 boosts a 7B model to an overall score of 67.0%, establishing a new state-of-the-art performance for open-source models.
  arXiv  Detail & Related papers  (2025-12-23T06:37:29Z)
• CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models [21.427373172124167]
  Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions.<n>We introduce CogMem, a memory-augmented LLM architecture that supports sustained iterative reasoning through structured, persistent memory.<n> Experiments on TurnBench show that this layered design mitigates reasoning failures, controls context growth, and improves consistency across extended reasoning chains.
  arXiv  Detail & Related papers  (2025-12-16T06:01:08Z)
• TeleMem: Building Long-Term and Multimodal Memory for Agentic AI [43.36544433800511]
  Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories.<n>We propose TeleMem, a unified long-term and multimodal memory system that maintains coherent user profiles through narrative dynamic extraction.<n>TeleMem surpasses the state-of-the-art Mem0 baseline with 19% higher accuracy, 43% fewer tokens, and a 2.1x speedup on the ZH-4O long-term role-play gaming benchmark.
  arXiv  Detail & Related papers  (2025-12-12T11:24:52Z)
• Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs [1.2582867366903179]
  We introduce Mnemosyne, an unsupervised, human-inspired long-term memory architecture for edge-based large language models (LLM)<n>Our approach uses graph-structured storage, modular substance and redundancy filters, memory committing and pruning mechanisms, and probabilistic recall with temporal decay and refresh processes modeled after human memory.<n>Mnemosyne is designed for use in longitudinal healthcare assistants, where repetitive and semantically similar but temporally distinct conversations are limited by naive retrieval.
  arXiv  Detail & Related papers  (2025-10-07T03:32:53Z)
• 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)
• Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers [58.98923344096319]
  REFORM is a novel inference framework that efficiently handles long contexts through a two-phase approach.<n>It achieves over 50% and 27% performance gains on RULER and BABILong respectively at 1M context length.<n>It also outperforms baselines on Infinite-Bench and MM-NIAH, demonstrating flexibility across diverse tasks and domains.
  arXiv  Detail & Related papers  (2025-06-01T23:49:14Z)
• 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.<n>But their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues.<n>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)

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.