AWorld加速智能体训练，让复杂任务的强化学习变得高效可行。
AWorld: Orchestrating the Training Recipe for Agentic AI
- 通过分布式集群并行交互，体验生成速度提升14.6倍。
- 基于Qwen3-32B的智能体在GAIA测试集上达32.23%准确率，超越GPT-4o。
- 开源系统与可复现成果，为智能体训练提供完整实用方案。
学习实践范式对构建强大智能体系统至关重要，但受限于低效的经验生成，尤其在复杂基准如GAIA上表现尤为明显。为此，我们提出AWorld——一个专为大规模智能体-环境交互设计的开源系统。通过将任务分布到集群中执行，AWorld相比标准单节点串行运行，经验收集速度提升14.6倍。这一关键加速使大规模强化学习变得实际且可扩展。基于此能力，我们训练了一个基于Qwen3-32B的智能体，在GAIA测试集上达到32.23%的pass@1准确率，优于GPT-4o（27.91%），接近DeepSeek-V3（31.89%）。我们的开源系统与所获智能体为完整的智能体训练流程提供了可落地的蓝图，涵盖高效交互到模型性能提升。
原文摘要 · Abstract (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 achieves pass@1 accuracy of 32.23% on the GAIA test set, which surpasses GPT-4o (27.91%) and rivals DeepSeek-V3 (31.89%). Our open-source system and the resulting agent provide a practical blueprint for a complete agentic AI training pipeline, from efficient interaction to demonstrable model improvement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。