ATLAS: All-round Testing of Long-context Abilities across Scales 事件

ATLAS: All-round Testing of Long-context Abilities across Scales arXiv:2605.28079v1 Announce Type: new Abstract: Long-context language models now advertise context windows up to millions of tokens, yet evaluations typically report a single length or a narrow task family, masking two failure modes: performance can collapse as length grows, and strong retrieval need not transfer to downstream use. We present ATLAS, a benchmarking framework that redefines long-context evaluation as length-dependen