product

ART (Agent Reinforcement Trainer)

productactiveart-agent-reinforcement-trainer--2ea4fac0·1 events·first seen 24d ago

Aliases: ART (Agent Reinforcement Trainer)

Co-occurring entities

More like this (12)

Agent Reasoning Evaluation (ARE)TRL (Transformer Reinforcement Learning)agent-teams-ai Agent-S Reference-Augmented Training tool-augmented language agents adversarial training RAT: Reference-Augmented Training for ASV Anti-Spoofing agent-skills AI Agents Arena AI TradingAgents

Recent events (1)

5Github Trending·24d ago·source ↗

OpenPipe ART: Agent Reinforcement Trainer for Multi-Step Agents via GRPO

OpenPipe has released ART (Agent Reinforcement Trainer), an open-source Python library for training multi-step agents on real-world tasks using GRPO (Group Relative Policy Optimization). The framework supports multiple model families including Qwen3, GPT-OSS, and Llama. With nearly 10k GitHub stars and 66 gained today, it is gaining notable community traction as a practical RL fine-tuning tool for agentic workflows.

Open Weights Progress Agent and Tool Ecosystem OpenPipe GRPO Llama +3 more