AI 精选动态
智能评分 60
Qwen 开源 AgentWorld-35B-A3B 模型和 AgentWorldBench
AI 推荐理由
这是 Qwen 将世界建模融入智能体训练的首个开源尝试，提供了高保真模拟环境，值得关注其技术路线与基准测试结果。核心解读
Qwen 开源了 Qwen-AgentWorld-35B-A3B (MoE, 35B 总参数, 3B 激活参数, 256K 上下文) 和 AgentWorldBench，旨在通过可扩展、可控的模拟器研究语言世界建模以提升通用智能体能力。
全文
wait, so is Qwen-AgentWorld-35B-A3B sort of Qwen3.7-35B-A3B? will test it
> **引用原帖 Qwen (@Alibaba_Qwen):**
> We open-source Qwen-AgentWorld-35B-A3B (MoE, 35B/3B active, 256K context) and AgentWorldBench.
> Two routes, one roadmap:
> 🔬 Build the simulator — scalable, controllable, surpassing real environments
> 🧠 Internalize world modeling — predict before you act
> Qwen-AgentWorld is our attempt to investigate how language world modeling can further expand the boundaries of general agent capabilities.
> Go build on it 🏃🏃♂️
> 📑 Paper: https://t.co/Jx2l5RKq71
> 📖 Blog: https://t.co/7tVcKyhsx2
> 💻 GitHub: https://t.co/B5Lvb1UZCn
> 🤗 HuggingFace: https://t.co/Kw3QBL1TM5
> 🧩 ModelScope: https://t.co/YBnGYgMWWI
> https://x.com/Alibaba_Qwen/status/2069720412481888400