[Feature Request] Add official Qwen3.5 Sokoban agentic example

Hi ROLL team,

Since support for Qwen3.5 has been added, could you please provide an official example for the Sokoban agentic pipeline (similar to the existing qwen2.5-vl-3B-agentic one)?

Specifically, a reference script like run_agentic_pipeline_sokoban.sh optimized for Qwen3.5 would be extremely helpful for the community to:

Verify the integration of the new model in RL environments.

Have a baseline configuration for training/evaluating Qwen3.5 on agentic tasks.

It would be great if this could be included in the examples/ directory.

Thanks!

Start by comparing the existing qwen2.5-vl-3B-agentic example with the requested run_agentic_pipeline_sokoban.sh reference script in the examples/ directory. Confirm the Qwen3.5 script supports the Sokoban agentic pipeline and provides a usable baseline for integration and training or evaluation.

Written by the indexing model from the issue text.