September1 Scaling MiMo on TPUs: From Optimized Inference to Large-Scale, Full-Parameter RL Date: September 21, 2026 | Estimated Reading Time: 21 min | Author: Peano AI Team
July1 rLLM: Reinforcement Learning for Language Agents Date: July 2, 2025 | Estimated Reading Time: 10 min | Author: Sijun Tan, Michael Luo, Colin Cai
July2 DeepSWE: Training a Fully Open-sourced, State-of-the-Art Coding Agent by Scaling RL Date: July 1, 2025 | Estimated Reading Time: 20 min | Author: Michael Luo, Naman Jain, Jaskirat Singh
April1 DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level Date: April 8, 2025 | Estimated Reading Time: 15 min | Author: Michael Luo, Sijun Tan, Roy Huang
February1 DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL Date: February 10, 2025 | Estimated Reading Time: 10 min | Author: Michael Luo, Sijun Tan
