Back to NewsAbsolute Zero: Reinforced Self-Play Reasoning with Zero DataMay 20, 2025ResearchAbsolute Zero: Reinforced Self-Play Reasoning with Zero Data, AI learns to reason by inventing and solving its own Python coding challenges, using RL, no human data needed. Author explanation: https://x.com/\_AndrewZhao/status/1919920459748909288.RelatedReasoning Features Learnt by SAEs Transfer Across ModelsGoogle Simula: Reasoning-Driven Synthetic DataScaling up test-time compute with latent reasoningPrevLLM Models Vibe Check & Benchmarks: OpenRouter, lmarena, and IQNextFlow-GRPO
