唐圣🥹
LotusDecoder@LotusDecoder·23h唐圣🥹Çevirjietang@jietangOur Single-rollout Asynchronous Optimization (SAO), is able to train stably for one thousand steps and consistently outperform GRPO and its variants on agentic coding and reasoning benchmarks, such as SWE-Bench Verified, BeyondAIME, and IMOAnswerBench. arxiv.org/pdf/2607.07508 日本語4082.8K
