← 최신 프로덕트

Terminal-Bench-RL

Training long-horizon terminal agents with RL. GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard. After training calculator agent via RL, I really wanted to go bigger!

오픈소스

419 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. ART

    github.com

    a new open-source RL framework for training agents

    Hacker News116점

  2. Superset

    superset.sh

    Terminal to run 10 parallel coding agents

    Hacker News96점

  3. NanoRL

    github.com

    RL training for LLMs in ~1,800 lines

    Hacker News11점

  4. RULER

    openpipe.ai

    Easily apply RL to any agent

    Hacker News81점

  5. OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview

    github.com

    Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/

    Hacker News393점