Resource-Aware Test-Time Scaling

ATEST (RATTS) makes self-consistency resource-aware. The same four-sample self-consistency query can use 4.1× more energy when the GPU is busy. ATEST-Online answers every query within budget. arXiv:2610.25519.

ATEST (RATTS) is resource-aware self-consistency for LLM inference. It adapts how many samples to draw to live GPU load. The same four-sample query can cost 4.1× more energy when the GPU is busy. arXiv:2610.25519.