paper-with-me

Papers

AWorld: Orchestrating the Training Recipe for Agentic AI

2025-08-28 · 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 arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.20404

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding

2026-03-17 · Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen 외 arxiv

Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often overlook the long tail topics and rely on po…

Reinforcement Learning

EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning

2026-06-02 · Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li 외 arxiv

Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes…

Reinforcement LearningMathematical ReasoningCode Generation

GigaWorld-0: World Models as Data Engine to Empower Embodied AI

2025-11-25 · GigaWorld Team, Angen Ye, Boyuan Wang, Chaojun Ni 외 arxiv

World models are emerging as a foundational paradigm for scalable, data-efficient embodied AI. In this work, we present GigaWorld-0, a unified world model framework designed explicitly as a data engine for Vision-Languag…

Video GenerationMotion Planning

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

2026-07-15 · GigaWorld Team, Angen Ye, Angyuan Ma, Boyuan Wang 외 arxiv

World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a…

rStar2-Agent: Agentic Reasoning Technical Report

2025-08-28 · Ning Shang, Yifei Liu, Yi Zhu, Li Lyna Zhang 외 arxiv

We introduce rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning to achieve frontier-level performance. Beyond current long CoT, the model demonstrates advanced cognitive behaviors, such …

Reinforcement Learning