arXiv AI
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 14
SETA: Scaling Environments for Terminal Agents
arXiv:2607. 10891v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs).
arXiv AI
Aug 19
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
LEGO-RL is a framework that connects native coding-agent harnesses with scalable policy‑gradient training without altering the harnesses’ internal flow. It achieves faithful optimization through in‑process LLM proxying, reliable execution via sandbox orchestration, and observable training with automated validation and a Live UI. Experiments show LEGO‑RL improves the Qwen3.5‑35B‑A3B model’s performance on three native harnesses while preserving high rollout‑training probability correlation.
arXiv AI
Jul 8
KAT-Coder-V2.5 Technical Report
arXiv:2607. 05471v1 Announce Type: cross Abstract: We present KAT-Coder-V2.
arXiv AI
Sep 10
EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent
arXiv:2609.05576v1 Announce Type: new Abstract: The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents that execute long-horizon tasks across statefu...
arXiv AI
Aug 7
CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
arXiv:2608. 05886v1 Announce Type: cross Abstract: Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it.
arXiv AI
Jun 3
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
arXiv:2512. 18552v3 Announce Type: replace-cross Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.