Add Qwen Agent World Model to Hub

[laxmareddyp]

Description of the change

Qwen-Agentworld : https://huggingface.co/collections/Qwen/qwen-agentworld, it is text only language model.

Qwen-AgentWorld:

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.

Reference

Colab Notebook

Checklist

• I have added all the necessary unit tests for my change.
• I have verified that my change does not break existing code and works with all backends (TensorFlow, JAX, and PyTorch).
• My PR is based on the latest changes of the main branch (if unsure, rebase the code).
• I have followed the Keras Hub Model contribution guidelines in making these changes.
• I have followed the Keras Hub API design guidelines in making these changes.
• I have signed the Contributor License Agreement.

[gemini-code-assist]

Code Review

This pull request adds support for text-only (language model only) variants of Qwen 3.5 MoE models. It updates the HuggingFace configuration converter to skip vision components when language_model_only is set, and updates the checkpoint conversion script to support text-only models by using AutoModelForCausalLM and precomputing text-only outputs. The review feedback suggests moving the AutoConfig import to the top of the checkpoint conversion script to adhere to PEP-8 guidelines.