CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
CodeMidas turns existing codebases into 5,545 executable RL coding tasks; GRPO-trained MiMo-V2.5 gains up to 17% on ProgramBench.
1 stories, newest first · one card per story
CodeMidas turns existing codebases into 5,545 executable RL coding tasks; GRPO-trained MiMo-V2.5 gains up to 17% on ProgramBench.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views