CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
[Sztuczna inteligencja] Autorzy: Bowen Ye, Lei Li, Shicheng Li i 16 więcej
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich source of such tasks, while existing methods typically rely on development artifacts such as issues and commits, limiting the range of tasks that can be extracted. To better scale RL environments, we present CodeMidas, an agentic pipeline that turns implemented functionality in existing codebases into executable RL environments using source code as its only task-specific input. CodeMidas allocates agentic compute to every stage of environment construction: agents explore implemented functionality to formulate behavioral specifications, construct tests grounded in execution of the original code, and validate and filter candidate tasks through execution checks and repeated solution rollouts. The resulting dataset has 5,545 training tasks from 3,…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja