# Alibaba — Qwen-AgentWorld: Language World Models for General Agents

- Company: Alibaba (alibaba.com)
- Announced: 2026-06-23T03:30:30+00:00
- Category: new-model
- Subject: Qwen
- Models affected: Qwen-AgentWorld, Qwen-AgentWorld-397B-A17B
- Source: https://qwen.ai/blog?id=qwen-agentworld
- Record: https://forck.live/items/4616-qwen-agentworld-language-world-models-for-general-agents

Alibaba releases Qwen-AgentWorld, a native language world model for simulating agent environments across seven domains, along with the AgentWorldBench benchmark. The model and benchmark are available on Hugging Face and ModelScope.

## Evidence

Verbatim from https://qwen.ai/blog?id=qwen-agentworld:

> Today we release Qwen-AgentWorld , a native language world model that simulates agent environments across seven domains:
> 
> Native world modeling: environment modeling is the training objective from continual pre-training onward (CPT → SFT → RL), not a post hoc adaptation on top of a general-purpose LLM.
> 
> Seven domains, one model: a single model simulates text-based (MCP, Search, Terminal, SWE) and GUI-based (Web, OS, Android) environments, with knowledge transferring across domains.
> 
> Together with the model, we release AgentWorldBench , a seven-domain evaluation benchmark with paired ground-truth observations from real environments.

---

Record: https://forck.live/items/4616-qwen-agentworld-language-world-models-for-general-agents
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md