Microsoft Research· Research / PhiResearch paper

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.

From the source

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).

microsoft.com