Guardado en:
Detalles Bibliográficos
Autores principales: Xia, Menglin, Zhang, Xuchao, Dixit, Shantanu, Harimurugan, Paramaguru, Wang, Rujia, Ruhle, Victor, Sim, Robert, Bansal, Chetan, Rajmohan, Saravan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.03315
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911418235748352
author Xia, Menglin
Zhang, Xuchao
Dixit, Shantanu
Harimurugan, Paramaguru
Wang, Rujia
Ruhle, Victor
Sim, Robert
Bansal, Chetan
Rajmohan, Saravan
author_facet Xia, Menglin
Zhang, Xuchao
Dixit, Shantanu
Harimurugan, Paramaguru
Wang, Rujia
Ruhle, Victor
Sim, Robert
Bansal, Chetan
Rajmohan, Saravan
contents Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scaling agent memory, yet it often comes at the cost of specificity, obscuring the fine-grained details required for effective reasoning. We introduce Memora, a harmonic memory representation that structurally balances abstraction and specificity. Memora organizes information via its primary abstractions that index concrete memory values and consolidate related updates into unified memory entries, while cue anchors expand retrieval access across diverse aspects of the memory and connect related memories. Building on this structure, we employ a retrieval policy that actively exploits these memory connections to retrieve relevant information beyond direct semantic similarity. Theoretically, we show that standard Retrieval-Augmented Generation (RAG) and Knowledge Graph (KG)-based memory systems emerge as special cases of our framework. Empirically, Memora establishes a new state-of-the-art on the LoCoMo and LongMemEval benchmarks, demonstrating better retrieval relevance and reasoning effectiveness as memory scales.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03315
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
Xia, Menglin
Zhang, Xuchao
Dixit, Shantanu
Harimurugan, Paramaguru
Wang, Rujia
Ruhle, Victor
Sim, Robert
Bansal, Chetan
Rajmohan, Saravan
Artificial Intelligence
Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scaling agent memory, yet it often comes at the cost of specificity, obscuring the fine-grained details required for effective reasoning. We introduce Memora, a harmonic memory representation that structurally balances abstraction and specificity. Memora organizes information via its primary abstractions that index concrete memory values and consolidate related updates into unified memory entries, while cue anchors expand retrieval access across diverse aspects of the memory and connect related memories. Building on this structure, we employ a retrieval policy that actively exploits these memory connections to retrieve relevant information beyond direct semantic similarity. Theoretically, we show that standard Retrieval-Augmented Generation (RAG) and Knowledge Graph (KG)-based memory systems emerge as special cases of our framework. Empirically, Memora establishes a new state-of-the-art on the LoCoMo and LongMemEval benchmarks, demonstrating better retrieval relevance and reasoning effectiveness as memory scales.
title Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
topic Artificial Intelligence
url https://arxiv.org/abs/2602.03315