{"ID":2876986,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20404","arxiv_id":"2508.20404","title":"AWorld: Orchestrating the Training Recipe for Agentic AI","abstract":"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.","short_abstract":"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-env...","url_abs":"https://arxiv.org/abs/2508.20404","url_pdf":"https://arxiv.org/pdf/2508.20404v2","authors":"[\"Chengyue Yu\",\"Siyuan Lu\",\"Chenyi Zhuang\",\"Dong Wang\",\"Qintong Wu\",\"Zongyue Li\",\"Runsheng Gan\",\"Chunfeng Wang\",\"Siqi Hou\",\"Gaochi Huang\",\"Wenlong Yan\",\"Lifeng Hong\",\"Aohui Xue\",\"Yanfeng Wang\",\"Jinjie Gu\",\"David Tsai\",\"Tao Lin\"]","published":"2025-08-28T04:04:30Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}