← Back to Model Beat
Models·2d ago·all news from November 19, 2026

Meta FAIR Self-Improving Memory Hits 56.0 on Continual Learning Bench

Researchers at Meta FAIR have developed a method for the Kimi-K2.6 model to autonomously generate and refine its own memory management instructions. By distilling these self-authored prompts directly into the model weights, the system achieved a score of 56.0 on the Continual Learning Bench, surpassing the 44.6 score set by traditional hand-written techniques.

Covered by 1 source

Related stories

ModelsAlibaba Unveils New Flagship AI Model in Riposte to US RivalsNov 16 · 28 sourcesModelsAnthropic Researcher Claims to Solve Riemann Problem With ClaudeNov 20 · 17 sourcesModelsIntroducing Gemini 4 NeonNov 18 · 8 sourcesModelsGoogle’s Gemini Can Now Control Mac Devices on Users’ BehalfNov 19 · 4 sources