AIBullisharXiv – CS AI · Feb 276/106
🧠
SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning
Researchers introduce SideQuest, a novel KV cache management system that uses Large Reasoning Models to compress memory usage during long-horizon AI tasks. The system reduces peak token usage by up to 65% while maintaining accuracy by having the model itself determine which tokens are useful to keep in memory.