ArXiv:2610.25519

ATEST / RATTS: Adaptive Resource-Aware Test-Time Scaling for LLM Inference (arXiv:2610.25519)
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.
Mobina Kashaniyan
Posted Oct 18, 2026 Large Language Models, High-Performance Computing, Energy Efficiency, Test-Time Scaling, Research Summary
ATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference
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.
Mobina Kashaniyan, Ali Jannesari
Posted Oct 18, 2026 Preprint, Large Language Models, High-Performance Computing, Energy Efficiency, Test-Time Scaling
PDF DOI PDF arXiv DOI Google Scholar Research Summary Local PDF

© 2026 Mobina Kashaniyan.