Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning

ArXi:2602.18922v2 Announce Type: replace-cross Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property -- cache effectiveness requires key consistency and precision,