Titans + MIRAS: Helping AI have long-term memory

Google Research introduces the Titans architecture and MIRAS framework, which enable AI models to update their core memory in real-time, combining the speed of RNNs with the accuracy of transformers. The approach uses a 'surprise metric' to selectively store novel information, allowing efficient handling of massive contexts.

From the source
We introduce the Titans architecture and the MIRAS framework, which allow AI models to work much faster and handle massive contexts by updating their core memory while it's actively running.
research.google

Visit source ↗research.google

Announced: 04 Dec 2025 19:26 UTC
Detected: 03 Aug 2026 21:12 UTC (+242d after)

Other stories

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AIResearch paper

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking trainingResearch paper

LG AI Research · 27 Aug[ACL 2026] ReSQL: A Self-Improving Text-to-SQL Framework through Retrieval-Augmented Error ReasoningResearch paper

xAI · 29 Aug

Grok Bot now works with X

Capability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update

GitHub · 28 AugGitHub Copilot weekly releases — August 24Capability change