arXiv cs.AIPaper
Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
The scaling problem is real: agents doing open-ended work need million-token context, but full attention becomes prohibitive. LSA clusters keys in a learned latent space so queries score clusters instead of every key, keeping accuracy while cutting cost. This is infrastructure-level work that could ship as a distillation method onto existing models. For builders, if your agent workflows are context-bound today, watch for when this reaches practitioners.