LongBench-v2

A new study from arXiv finds that query-aware prompt compression, which invalidates prefix caches on every call, can be more expensive than naive caching under realistic hit rates on Anthropic's Sonne…

Researchers propose a value-of-information router for block-sparse attention that dynamically doubles the kept key blocks when the top-k selection is uncertain, improving recall on LongBench-v2 from 0…

Stanford researchers introduced Decentralized Language Models (DeLM), a multi-agent framework that enables AI agents to coordinate without a central controller, achieving a 10.5 percentage point impro…