Research
All posts tagged with #Research
10 Files Beat 413: What Anthropic's Dreaming Agents Teach Us About Memory
Anthropic's Pokémon memory benchmark shows a model with 10 well-curated memory files beating one with 413. What 'dreaming' agents reveal about curation as the real memory capability.
Stop Deleting Frames: The Memory Pattern That Made a Vision Agent Beat Humans
MIT's VISTA harness beat first-time humans on a visual puzzle benchmark by storing every frame it saw instead of deleting them. Pull frame storage out and its score falls from 99 to 70 with the same model. The pattern works for your agents too.
Your agent doesn't need a bigger context window. It needs a better memory.
An NVIDIA team showed agents can match full long-context accuracy with aggressive compaction, cutting costs up to 54.6x. Here's how to put that to work in your own stack.
One Encoder, Two Jobs: UltraBERT and the End of Scaling Your Embedder
UltraBERT tops 9 of 10 encoder benchmarks at 150M and 380M parameters with a 32K context, and the research behind it proves more pretraining compute stopped helping encoders long ago. Here is what that changes for your RAG pipeline.