CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Ranking
Overall
84
Content
90
Popularity
70
Observed public metrics from 1 member.
Merged summary
TL;DR - CodeMidas converts implemented functionality in open-source codebases into verified reinforcement-learning environments for coding agents using only source code. Its 5,545-task dataset improved a trained model across issue repair, program construction, and terminal-work benchmarks.
- Agentic stages generate behavioral specifications, execution-grounded tests, and validated tasks through repeated solution rollouts.
- The dataset spans 3,185 repositories, 23 programming languages, and 15 technical domains.
- GRPO training of MiMo-V2.5 yielded gains of 11.7% on DeepSWE, 17% on ProgramBench, and 8.5% on Terminal-Bench v2.1.
- Trained agents explored codebases more extensively and used more diverse self-verification behaviors.
Sources (1)
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Public signals
Hugging Face upvotes 131
TL;DR - CodeMidas converts implemented functionality in open-source codebases into verified reinforcement-learning environments for coding agents using only source code. Its 5,545-task dataset improved a trained model across issue repair, program construction, and terminal-work benchmarks.
- Agentic stages generate behavioral specifications, execution-grounded tests, and validated tasks through repeated solution rollouts.
- The dataset spans 3,185 repositories, 23 programming languages, and 15 technical domains.
- GRPO training of MiMo-V2.5 yielded gains of 11.7% on DeepSWE, 17% on ProgramBench, and 8.5% on Terminal-Bench v2.1.
- Trained agents explored codebases more extensively and used more diverse self-verification behaviors.