Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| 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 |