MobileSpec Trains LLM Specialists on iPhones Using Forward Passes Only
Skipping backpropagation means on-device fine-tuning no longer needs training-grade memory, letting a shared 8B model be personalized overnight on consumer hardware like an iPhone 16 Pro. The 89-100% success-rate jump for a phone-use agent suggests practical deployment paths for on-device agents handling private data. Practitioners working on edge AI, quantization or RLVR-style training should examine FuRA-S as an alternative to LoRA-based ES methods.