Guardado en:
Detalles Bibliográficos
Autores principales: Zhou, Yue, Guo, Xiaobo, Bayar, Belhassen, Sengamedu, Srinivasan H.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.06282
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918281180348416
author Zhou, Yue
Guo, Xiaobo
Bayar, Belhassen
Sengamedu, Srinivasan H.
author_facet Zhou, Yue
Guo, Xiaobo
Bayar, Belhassen
Sengamedu, Srinivasan H.
contents Long-term conversational agents face a fundamental scalability challenge as interactions extend over time: repeatedly processing entire conversation histories becomes computationally prohibitive. Current approaches attempt to solve this through memory frameworks that predominantly fragment conversations into isolated embeddings or graph representations and retrieve relevant ones in a RAG style. While computationally efficient, these methods often treat memory formation minimally and fail to capture the subtlety and coherence of human memory. We introduce Amory, a working memory framework that actively constructs structured memory representations through enhancing agentic reasoning during offline time. Amory organizes conversational fragments into episodic narratives, consolidates memories with momentum, and semanticizes peripheral facts into semantic memory. At retrieval time, the system employs coherence-driven reasoning over narrative structures. Evaluated on the LOCOMO benchmark for long-term reasoning, Amory achieves considerable improvements over previous state-of-the-art, with performance comparable to full context reasoning while reducing response time by 50%. Analysis shows that momentum-aware consolidation significantly enhances response quality, while coherence-driven retrieval provides superior memory coverage compared to embedding-based approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06282
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning
Zhou, Yue
Guo, Xiaobo
Bayar, Belhassen
Sengamedu, Srinivasan H.
Computation and Language
Artificial Intelligence
Long-term conversational agents face a fundamental scalability challenge as interactions extend over time: repeatedly processing entire conversation histories becomes computationally prohibitive. Current approaches attempt to solve this through memory frameworks that predominantly fragment conversations into isolated embeddings or graph representations and retrieve relevant ones in a RAG style. While computationally efficient, these methods often treat memory formation minimally and fail to capture the subtlety and coherence of human memory. We introduce Amory, a working memory framework that actively constructs structured memory representations through enhancing agentic reasoning during offline time. Amory organizes conversational fragments into episodic narratives, consolidates memories with momentum, and semanticizes peripheral facts into semantic memory. At retrieval time, the system employs coherence-driven reasoning over narrative structures. Evaluated on the LOCOMO benchmark for long-term reasoning, Amory achieves considerable improvements over previous state-of-the-art, with performance comparable to full context reasoning while reducing response time by 50%. Analysis shows that momentum-aware consolidation significantly enhances response quality, while coherence-driven retrieval provides superior memory coverage compared to embedding-based approaches.
title Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.06282