Mark Kretschmann(@mark_k):Coding agents can now create their own training environments from existing software! Xiaomi's new CodeMidas system lets agents inspect open-source projects, extract coding tasks, build execution-based tests, and discard broken or exploitable tasks. It generated 5,545 verified RL environments from 3,185 projects across 23 programming languages. According to the paper, training MiMo-V2.5 on these tasks improved issue repair by 11.7%, whole-program construction by 17%, and Terminal-Bench performance by 8.5%. Instead of humans writing every RL task by hand, CodeMidas can continuously mine existing software for new, verifiable training tasks.

2026.09.21 10:41

Coding agents can now create their own training environments from existing software! Xiaomi's new CodeMidas system lets agents inspect open-source projects, extract coding tasks, build execution-based tests, and discard broken or exploitable tasks. It generated 5,545 verified RL environments from 3,185 projects across 23 programming languages. According to the paper, training MiMo-V2.5 on these tasks improved issue repair by 11.7%, whole-program construction by 17%, and Terminal-Bench performance by 8.5%. Instead of humans writing every RL task by hand, CodeMidas can continuously mine existing software for new, verifiable training tasks.

显示更多