Hugging Face's logo

Xkev
/
mc_society

Image-Text-to-Text
Transformers
Safetensors
English
minecraft
multi-agent
qwen3-vl
Model card Files
xet
 Community

Qwen3-VL-4B-Instruct — Minecraft Three-Agent MPT

Paper: Learning Self-Orchestration in Decentralized Agent Swarms

Code: https://github.com/Embodied-Minds-Lab/MPT

For the SFT cold start, see Xkev/mc_society_sft.

For the single-agent counterpart, see Xkev/mc_single.

Training

  • Initialization: Xkev/mc_society_sft
  • Dataset: Minecraft iron-pickaxe tasks
  • Framework: verl
  • Algorithm: MPT
  • Hyperparameters: lr=1e-6, lr_warmup_ratio=0, constant schedule

Intended use

Research on multi-agent post-training and embodied agents. Not intended for general dialog or production.

License

Apache-2.0.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Xkev/mc_society

Base model

Qwen/Qwen3-VL-4B-Instruct
Finetuned
(495)
this model

Paper for Xkev/mc_society