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 3,185 open-source codebases spanning 23 programming languages and 15 technical domains. Training MiMo-V2.5 on these tasks with GRPO improves performance on all five diverse benchmarks, covering issue repair (DeepSWE + 11.7%), whole-program construction (ProgramBench +17%), and terminal work (Terminal-Bench v2.1 +8.5%). Ablations show that increasing the number of high-quality training tasks improves performance. Trajectory analysis shows the RL-trained agent demonstrates better behaviors like increasing codebase exploration and more diverse self-verification. These results establish source code as a scalable foundation for constructing RL environments that improve coding agents across diverse software tasks.
This work introduces Compositional Environment Scaling (\textbf{CompoWorld}), which expands the task space by composing a finite library of reusable services, and guides reinforcement learning toward full task completion by emphasizing criteria with lower pass rates within each rollout group.
Xiao-Wen Yang, Wei-Yi Xu, Wen Da et al.· arXiv.org· 1 citation
Large language models for code generation often fail on execution, multilingual coverage, and contamination control, especially under frozen backbone constraints. We present CodeForge-MA, a unified framework that improves code synthesis through a multi-agent data forge, execution verified reinforced instruction tuning,...
Zhi-Zhou Gu, Xian-Ting Wu, Si-Yu Gu et al.· 2026 8th International Confe...· 0 citations
CodeActionBench is introduced, a benchmark of 25 manipulation tasks that evaluates this capability through agentic Code-as-Policy and provides a controlled testbed for measuring how general-purpose models translate their capabilities into manipulation behavior and for examining typical failure scenarios in that process...
Yiheng Lyu, Xueying Jiang, Wen-Hao Li et al.· arXiv.org· 3 citations
RACaP is introduced, an agentic framework that moves coding to evolution and uses a Reasoning-and-Acting loop to call frozen, typed Policy APIs at deployment and shows that separating reusable code from runtime decisions supports continued evolution, effective transfer, and efficient long-horizon control.
Coding agents solve repository-level software engineering tasks through long trajectories of code inspection, search, editing, and testing. As a task progresses, earlier exploration becomes stale, so managing context is more than avoiding overflow: an agent must decide when to compact, what working state to preserve, a...
Xuan Zhang, Long-Tao Zheng, Cun-Xiao Du et al.· 7 citations
Coding agents are beginning to develop the production-grade AI infrastructure that trains and serves large models, yet existing benchmarks cover only single kernels or single-GPU tasks, and grade with tests and prompts that misjudge both correct and incorrect patches. We introduce InfraDev, a benchmark of 36 tasks buil...
Yang-Shen Deng, Jia-Qi Ruan, Ye-Qi Huang et al.· 0 citations