PUBLICATION: CacheNotes: Task-aware key-value cache compression for reasoning-intensive knowledge tasks
Copyright ACL. Personal use of this material is permitted. The definitive version of this paper was published in EACL 2026, 19th Conference of the European Chapter of the Association for Computational Linguistics, 24-29 March 2026, Rabat, Morocco and is available at : http://dx.doi.org/10.18653/v1/2026.eacl-long.309