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

Sunil Tiwari; Payal Fofadiya

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

Computer Vision and Pattern Recognition 2026-04-01 v1 Artificial Intelligence

Authors: Sunil Tiwari , Payal Fofadiya

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.

Keywords

Large Language Models memory architecture long-term retention context management multi-layer memory

Cite

@article{arxiv.2603.29194,
  title  = {Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention},
  author = {Sunil Tiwari and Payal Fofadiya},
  journal= {arXiv preprint arXiv:2603.29194},
  year   = {2026}
}

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

Abstract

Keywords

Cite

Related papers