# Microsoft Research — Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

- Company: Microsoft Research (microsoft.com)
- Announced: 2026-06-29T21:14:22+00:00
- Category: research-paper
- Subject: Research / Phi
- Source: https://www.microsoft.com/en-us/research/blog/memora-a-harmonic-memory-representation-balancing-abstraction-and-specificity/
- Record: https://forck.live/items/2462-memora-a-harmonic-memory-representation-balancing-abstraction-and-specificity

Memora is a scalable memory system for long-horizon AI agents that decouples rich memory content from lightweight retrieval, achieving state-of-the-art results on LoCoMo and LongMemEval benchmarks while using up to 98% fewer context tokens. The paper is published at ICML 2026 and code is available on GitHub.

## Evidence

Verbatim from https://www.microsoft.com/en-us/research/blog/memora-a-harmonic-memory-representation-balancing-abstraction-and-specificity/:

> Memora is a scalable memory system that dramatically increases agent productivity on long-horizon tasks by decoupling what is stored (rich memory content) from how it’s retrieved (lightweight abstractions and cue anchors), balancing abstraction and specificity. Memora sets new state-of-the-art on LoCoMo and LongMemEval, outperforming Mem0, RAG, and full-context inference while using up to 98% fewer context tokens. Memora paper (opens in new tab) is published at ICML 2026. Memora code is available at https://github.com/microsoft/Memora (opens in new tab).

---

Record: https://forck.live/items/2462-memora-a-harmonic-memory-representation-balancing-abstraction-and-specificity
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md