AWorld: Orchestrating the Training Recipe for Agentic AI

yuchengyue, Siyuan Lu (SII), chenyi zhuang, Dong Wang, Qing Wu, Zongyue Li, Runsheng Gan, Chunfeng Wang, Hou, Gaochi Huang, Yan, Lifeng Hong, xue, wang yan feng, Jinjie Gu, David Tsai, Tao Lin

AWorld: Orchestrating the Training Recipe for Agentic AI: 33 upvotes on Hugging Face Daily Papers, #5 of 19 papers on 2025-08-29. Day-by-day upvote history. It lost 6 votes when the Hub removed votes in bulk.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.