AWorld：精心编排智能体AI的训练方案

摘要

实践学习范式对于开发具备能力的自主AI系统至关重要，然而其发展却因经验生成效率低下而严重受阻，这一瓶颈在GAIA等复杂基准测试中尤为突出。为解决这一问题，我们推出了AWorld，一个专为大规模智能体-环境交互设计的开源系统。通过将任务分布至集群执行，AWorld相较于标准的单节点顺序执行，将经验收集速度提升了14.6倍。这一关键性加速使得广泛的强化学习变得切实可行且可扩展。利用这一能力，我们训练了一个基于Qwen3-32B的智能体，其表现显著超越了基础模型，将GAIA整体准确率从21.59%提升至32.23%。在基准测试最具挑战性的层级上，我们的智能体取得了16.33%的得分，超越了领先的专有模型性能。我们的开源系统及其成果智能体，为从高效交互到可验证模型改进的完整自主AI训练流程，提供了一个实用的蓝图。

English

The learning from practice paradigm is crucial for developing capable Agentic AI systems, yet it is severely hampered by inefficient experience generation, a bottleneck especially pronounced in complex benchmarks like GAIA. To address this, we introduce AWorld, an open-source system engineered for large-scale agent-environment interaction. By distributing tasks across a cluster, AWorld accelerates experience collection by 14.6x compared to standard single-node, sequential execution. This critical speedup makes extensive reinforcement learning practical and scalable. Leveraging this capability, we trained a Qwen3-32B-based agent that significantly outperforms its base model, increasing its overall GAIA accuracy from 21.59% to 32.23%. On the benchmark's most challenging levels, our agent achieves a score of 16.33%, surpassing the performance of leading proprietary models. Our open-source system and resulting agent provide a practical blueprint for a complete agentic AI training pipeline, from efficient interaction to demonstrable model improvement.

AWorld：精心编排智能体AI的训练方案

AWorld: Orchestrating the Training Recipe for Agentic AI

摘要

Support