评分 6.5 · 来源:cs.LG updates on arXiv.org · 发布于 2026-04-17
评分依据:Test-time compute allocation via constrained policy optimization, timely topic given the importance of TTC scaling
arXiv:2604.14853v1 Announce Type: new Abstract: Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improving large language model performance.