460 citations · 535 across the 16 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU
Di Chai, Leye Wang, Zeshen Su +2
Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV capacity and the model's native context window. Existing systems typically compa…
cs.DC2026
PrefixFlow: Training-Time KV Caching for Schedule-Level Prefix Reuse in LLM RL Training
Pengbo Li, Feiyuan Zhang, Guangming Sheng +8
In reinforcement learning (RL) post-training, one prompt fans out into trajectories, yet standard trainers replay the shared prefix's forward and backward pass times; in lo…