Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
Menglin Xia, Xuchao Zhang, Shantanu Dixit, Paramaguru Harimurugan, Rujia Wang, Victor Ruhle, Robert Sim, Chetan Bansal, Saravan Rajmohan

TL;DR
Memora introduces a novel memory system that balances abstraction and specificity, improving retrieval relevance and reasoning in scalable agent memory, outperforming existing methods on key benchmarks.
Contribution
We propose Memora, a structurally harmonic memory representation that balances abstraction and specificity, and demonstrate its theoretical and empirical advantages over existing systems.
Findings
Achieves state-of-the-art results on LoCoMo and LongMemEval benchmarks.
Enhances retrieval relevance and reasoning effectiveness.
Unifies RAG and KG-based memory systems as special cases.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · AI-based Problem Solving and Planning · Personal Information Management and User Behavior
