MODEL PROFILE

Qwen-AgentWorld-35B-A3B

阿里巴巴 · Qwen · Qwen-AgentWorld-35B-A3B

> [!Note] > This repository contains the model weights and configuration files for **Qwen-AgentWorld-35B-A3B**, a native language world model trained for agentic environment simulation. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc. **Qwen-AgentWorld** is the first language world model to cover seven agent interaction domains within a single model. It simulates agentic environments via long chain-of-thought reasoning, predicting the next environment state given an agent's action and interaction history. Trained through a three-stage pipeline — CPT injects environment knowledge, SFT activates next-state-prediction reasoning, RL sharpens simulation fidelity — Qwen-AgentWorld is a **native world model**: environment modeling is the training objective from the CPT stage onward, not a post-hoc add-on. Qwen-AgentWorld-35B-A3B can be served via APIs with popular inference frameworks. In the following, we show example commands to launch OpenAI-compatible API servers.

Text generationlicense:apache-2.0
Context window262,144 Token
Input → OutputText → Text
Model weightsNot verified
Profile updated2026/10/30 10:22:53
OVERVIEW

Model overview

> [!Note] > This repository contains the model weights and configuration files for **Qwen-AgentWorld-35B-A3B**, a native language world model trained for agentic environment simulation. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc. **Qwen-AgentWorld** is the first language world model to cover seven agent interaction domains within a single model. It simulates agentic environments via long chain-of-thought reasoning, predicting the next environment state given an agent's action and interaction history. Trained through a three-stage pipeline — CPT injects environment knowledge, SFT activates next-state-prediction reasoning, RL sharpens simulation fidelity — Qwen-AgentWorld is a **native world model**: environment modeling is the training objective from the CPT stage onward, not a post-hoc add-on. Qwen-AgentWorld-35B-A3B can be served via APIs with popular inference frameworks. In the following, we show example commands to launch OpenAI-compatible API servers.

Key features

特点摘要待依据来源补齐,不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。