Guardado en:
Detalles Bibliográficos
Autores principales: Borro, Luiz C., Macarini, Luiz A. B., Tindall, Gordon, Montero, Michael, Struck, Adam B.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.19935
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908902772178944
author Borro, Luiz C.
Macarini, Luiz A. B.
Tindall, Gordon
Montero, Michael
Struck, Adam B.
author_facet Borro, Luiz C.
Macarini, Luiz A. B.
Tindall, Gordon
Montero, Michael
Struck, Adam B.
contents As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely on injecting large volumes of raw conversation into prompts, leading to high token costs and degraded performance. We introduce Memori, an LLM-agnostic persistent memory layer that treats memory as a data structuring problem. Its Advanced Augmentation pipeline converts unstructured dialogue into compact semantic triples and conversation summaries, enabling precise retrieval and coherent reasoning. Evaluated on the LoCoMo benchmark, Memori achieves 81.95% accuracy, outperforming existing memory systems while using only 1,294 tokens per query (~5% of full context). This results in substantial cost reductions, including 67% fewer tokens than competing approaches and over 20x savings compared to full-context methods. These results show that effective memory in LLM agents depends on structured representations instead of larger context windows, enabling scalable and cost-efficient deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19935
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents
Borro, Luiz C.
Macarini, Luiz A. B.
Tindall, Gordon
Montero, Michael
Struck, Adam B.
Machine Learning
As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely on injecting large volumes of raw conversation into prompts, leading to high token costs and degraded performance. We introduce Memori, an LLM-agnostic persistent memory layer that treats memory as a data structuring problem. Its Advanced Augmentation pipeline converts unstructured dialogue into compact semantic triples and conversation summaries, enabling precise retrieval and coherent reasoning. Evaluated on the LoCoMo benchmark, Memori achieves 81.95% accuracy, outperforming existing memory systems while using only 1,294 tokens per query (~5% of full context). This results in substantial cost reductions, including 67% fewer tokens than competing approaches and over 20x savings compared to full-context methods. These results show that effective memory in LLM agents depends on structured representations instead of larger context windows, enabling scalable and cost-efficient deployment.
title Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents
topic Machine Learning
url https://arxiv.org/abs/2603.19935