Announcement_4
Our paper Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search 【新智元】 has been accepted to ICML 2025.
Our paper Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search 【新智元】 has been accepted to ICML 2025.