Researchers automated LLM reasoning strategy design and cut token usage by 69.5% (opens in new tab)

Test-time scaling (TTS) has emerged as a proven method to improve the performance of large language models in real-world applications by giving them extra compute cycles at inference time. However, TTS strategies have historically been handcrafted, relying heavily on human intuition to dictate the rules of the model’s reasoning. To address this bottleneck, researchers from Meta, Google, and several universities have introduced By implementing the optimal strategies discovered by AutoTTS, orga...