# Qwen-AgentWorld 超越 Claude Opus 4.8 和 GPT-5.4

- 来源：Alibaba Cloud (@alibaba_cloud)
- 发布时间：2026-06-24 18:20
- AIHOT 分数：69
- AIHOT 链接：https://aihot.virxact.com/items/cmqrxc02g0ozzslp5okdi2ley
- 原文链接：https://x.com/alibaba_cloud/status/2069727249335775256

## AI 摘要

阿里云发布 Qwen-AgentWorld，一个原生语言世界模型，可在单一模型内模拟 7 种智能体环境（MCP、搜索、终端、SWE、Web、OS、Android），环境建模是其初始训练目标而非事后适配。该模型

## 正文

📣📣 Meet Qwen-AgentWorld - a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training objective from day one, not a post-hoc adaptation.

🤔 LLMs are trained to be better agents - better at acting in environments. But nobody has trained them to model the environments themselves.

🗺️ Our roadmap: investigate how language world modeling can push the boundaries of general agent capabilities, along two routes:

1️⃣ Build a foundation model for environment simulation - outperforming Claude Opus 4.8 and GPT-5.4 on AgentWorldBench

2️⃣ Investigate how world modeling enhances agent training:
🔬 Controllable Sim RL (agentic RL with LWM as environments) surpasses training in real environments
🧠 Learning to predict environments (LWM warm-up) makes agents stronger - remarkably, even without any agent-specific training, this predictive knowledge transfers to agentic tasks with zero fine-tuning

🔗 Model Studio: https://int.alibabacloud.com/m/1000413253/