Azizbek8189/Qwen-AgentWorld-35B-A3B
Qwen-AgentWorld-35B-A3B is a 35.1 billion parameter native language world model developed by Qwen, designed for agentic environment simulation. It is the first language world model to unify seven interaction domains, including tool calling, search, and software engineering. This model excels at predicting environment states given an agent's actions, making it a generalizable and scalable simulator for agent development.
Loading preview...
Qwen-AgentWorld-35B-A3B: A Native Language World Model
Qwen-AgentWorld-35B-A3B is a 35.1 billion parameter language world model (LWM) developed by Qwen, specifically engineered for simulating agentic environments. Unlike general-purpose LLMs, environment modeling is its core training objective from the initial Continual Pre-Training (CPT) stage, followed by Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to enhance simulation fidelity.
Key Capabilities
- Unified Agent Interaction Domains: Covers seven distinct domains within a single model: MCP (tool calling), Search, Terminal, SWE (software engineering), Android, Web, and OS, supporting both text and GUI interactions.
- Native World Model Design: Built from the ground up for environment modeling, predicting the next environment state based on agent actions and interaction history.
- Generalizable & Controllable Simulation: Demonstrates zero-shot generalization to out-of-distribution environments and allows for controllable perturbations and fictional-world construction.
- Agent Foundation Model: Provides a strong foundation for agentic tasks, with RL warm-up transferring to multi-turn, tool-calling scenarios across seven benchmarks, including three entirely out-of-domain.
- Extended Context Length: Features a substantial context length of 262,144 tokens, crucial for multi-turn environment simulation.
Use Cases
- Agent Development and Testing: Ideal for simulating complex environments to train and evaluate AI agents.
- Interactive Environment Modeling: Can predict outcomes in various digital environments, from command-line interfaces to web browsing.
- Research in Agentic AI: Provides a robust platform for exploring and advancing language world models and agent intelligence.