← 최신 프로덕트

ART

a new open-source RL framework for training agents. Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more! ART is a new open-source framework for training agents using reinforcement learning (RL).

라이브러리오픈소스

10,836 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. SkillGraph

    github.com

    Open-source agentic framework with skills instead of tools

    Hacker News19점

  2. Next-Gen AI Training

    github.com

    LLM-RLHF-Tuning with PPO and DPO

    Hacker News30점

  3. I RL-trained an agent that trains models with RL (for ~$1.3k)

    github.com

    RL-training an AI agent to RL-train AI agents.

    Hacker News107점

  4. RULER

    openpipe.ai

    Easily apply RL to any agent

    Hacker News81점

  5. Llama-8B Teaches Itself Baby Steps to Deep Research Using RL

    github.com

    Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

    Hacker News39점