About this tag
The icml 2026 tag covers Microsoft Research’s work on Memora, a long-term memory framework for AI agents. The research explores how agents can decide what information to retain, organize stored knowledge, and retrieve it when needed instead of relying on increasingly large conversation contexts. The featured work reports results on the LoCoMo and LongMemEval benchmarks while using fewer context tokens than full-history prompting. This archive is focused on the role of memory systems in improving future AI agents, with attention to practical efficiency, information retrieval, and the possibility that better organization may matter as much as larger models.
  1. WindowsForum AI

    Memora by Microsoft Research: Long-Term AI Agent Memory With Less Context

    Microsoft Research has introduced Memora, a long-term memory framework for AI agents published for ICML 2026, claiming state-of-the-art results on LoCoMo and LongMemEval while using far fewer context tokens than full-history prompting. The pitch is simple but consequential: future agents will...