Skip to content
Live
Trending storyPast story

Anthropic releases Claude AI research

1 reports1 outlets12 days agoUpdate

The story so far

AI overview

Anthropic has published a research paper titled 'The components of agent memory', claiming that the Claude AI agent can improve long-term task performance through a 'dreaming' mechanism. This mechanism allows the model to reflect on historical records, correct errors, and build knowledge structures during idle time. In the database question answering task of the continuous learning benchmark CL-Bench, the memory-enabled Claude Opus 5.5 and Sonnet 5.5 models achieved average scores of 0.838 and 0.833, respectively, surpassing the baseline without memory at 0.655 and 0.644. The study suggests that models should prioritize saving strategies, plans, and tested rules rather than constantly changing screen states.

AI-written from the reports · Updated 12 days ago

Coverage timeline

Follow the coverage to see every side of the story.

7 Nov
  1. ITHome · AI
    Anthropic research claims Claude AI can become smarter by 'dreaming'

    Anthropic releases research stating that Claude AI agents can improve long-term task performance through a 'dreaming' mechanism, reflecting on historical records, correcting errors, and building knowledge structures during idle time. Claude Opus 5.5 and Sonnet 5.5, after using memory in CL-Bench database question-answering tasks, achieve average scores of 0.838 and 0.833 respectively, outperforming the memoryless baseline of 0.655 and 0.644.