Xiaomi's CodeMidas mines open-source code into 5,545 verified RL environments, boosting MiMo-V2.5 benchmarks
mark_k · x · 2026-09-21
Xiaomi's new CodeMidas system lets coding agents create their own training environments from existing software: agents inspect open-source projects, extract coding tasks, build execution-based tests, and discard broken or exploitable ones.
- Generated 5,545 verified RL environments from 3,185 projects across 23 programming languages
- Training MiMo-V2.5 on these tasks improved issue repair by 11.7%, whole-program construction by 17%, and Terminal-Bench by 8.5%
Instead of humans hand-writing every RL task, CodeMidas continuously mines existing software for new, verifiable training tasks — addressing a key RL data bottleneck.
More from coding & agent
- Photoroom reclaims ~1,000 idle GPU hours a week with SkyPilot across Slurm and Kubernetes — skypilot_org · 2026-11-12
- Google launches Gemini Decisions API: scores 1,000 questions per pass, output tokens free — dean_rie · 2026-11-12
- Zed v1.28 adds background auto-fetch for current and default branch remotes — dean_rie · 2026-11-12
- Indie Britpop AI music video built with Nano Banana Pro, Kling, and free lip-sync via WAN2GP + LTX 2.5 — cocktailpeanut · 2026-11-12
- Cloudflare Talk: Swapping Some Agent LLM Calls for Fast Models Like Jev Gives Big Speedups — michellechen · 2026-11-12
- Engineer Curates 15 AI Agent Design Patterns Across Single-Agent, Multi-Agent and Feedback Tiers — MaryamMiradi · 2026-11-12