Qwen-AgentWorld-35B-A3B-GGUF

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

Qwen-AgentWorld-35B-A3B

📑 Technical Report |
📖 Blog |
🤗 Hugging Face |
🤖 ModelScope |
💻 GitHub |
🖥️ Demo

> [!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.

Highlights

• Seven Unified Domains. A single model covers MCP (tool calling), Search, Terminal, SWE (software engineering), Android, Web, and OS — spanning both text and GUI interaction environments.
• Native World Model. Environment modeling from CPT onward, not post-hoc adaptation on a general-purpose LLM.
• Generalizable, Scalable & Controllable Simulator. Zero-shot generalization to OOD environments (e.g., OpenClaw); controllable perturbations and fictional-world construction surpass real-environment training.
• Agent Foundation Model. LWM RL warm-up on single-turn, non-agentic trajectories transfers to multi-turn, tool-calling agentic tasks across 7 benchmarks, including 3 entirely out-of-domain.

Model Overview

• Type: Causal Language Model (Languag…

Source: https://huggingface.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF