HySparse2: Hybrid Sparse Attention with Two-Level KV Sharing

Excerpt

arXiv:2609.26368v1 Announce Type: new Abstract: Long-horizon and multi-turn agents typically generate short actions and process long observations from tools and environments. This growing context demands efficient prefill, compact KV-cache storage, and accurate long-context retrieval. To meet these demands, we introduce HySparse2, a hybrid sparse attention architecture with two-level KV sharing. At the outer level, KV Bridging adopts a YOCO-style self-decoder and cross-decoder structure, but bri