Author name: Divya Shyamal, Marta Kne\v{z}evi\'c, Lan Tran, Chanakya Ekbote, Vijay Lingam, Paul Pu Liang

arXiv:2604.16535v2 Announce Type: replace
Abstract: Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple cand…

arXiv:2604.16535v1 Announce Type: new
Abstract: Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple candidat…