Xiaomi's CodeMidas turns source code into RL environments, doubling DeepSWE to 21.7%
maier_ak · x · 2026-09-22
Xiaomi's MiMo team released CodeMidas, an agentic pipeline that converts existing open-source codebases into executable RL training environments for coding agents.
- Key idea: prior methods rely on development artifacts like issues and commits; CodeMidas uses source code alone. Agents explore implemented functionality to draft behavioral specs, build tests grounded in the original code's execution, then validate and filter tasks via execution checks and repeated solution rollouts.
- Scale: 5,545 training tasks from 3,185 open-source repos across 23 programming languages and 15 technical domains.
- Results: training MiMo-V2.5 with GRPO improves all five benchmarks, including DeepSWE +11.7% (reported as doubling from 10.0% to 21.7%), ProgramBench +17%, and Terminal-Bench v2.1 +8.5%.
- Why it matters: a scalable way to generate RL environments for coding agents without needing issue/commit metadata. Paper: arXiv 2609.22068.
More from coding & agent
- 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
- Google Antigravity rolls out browser use, closing the loop from research to coding to live verification — rseroter · 2026-11-12
- Prettier 3.10 ships new Flow/JS syntax and a Zig-powered Yuku plugin — Vjeux · 2026-11-12
- YC-backed Graphide claims CI runner 10-20x faster than GitHub on 24 repos — ycombinator · 2026-11-12