mlsanityData to 14 Oct 2026

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

arXiv 2603.29194 ↗First posted 31 Mar 2026cs.CV cs.AIcited by 2

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 8 of its 22 references that are in the map. First posted on arXiv 31 Mar 2026.

Builds on

8 of 22 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Memory OS of AI Agent30 May
  2. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model18 Aug
  3. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb
  4. 2024InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory7 Feb

Other references · 4

  1. 2025LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocationcited by 16
  2. 2024In-Context Former: Lightning-fast Compressing Context for Large Language Modelcited by 12
  3. 2025Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational Historycited by 10
  4. 2026ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systemscited by 1
  2. 2026CreaMem: A Scene-Aware Memory Architecture for Personalized Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
  2. 2026Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents
  3. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents
  4. 2026AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
  5. 2026AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
  6. 2026MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents
  7. 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents
  8. 2026CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents