• Overview
• Installation
  • Besiege Environment Setup
  • AgenticFlow Installation
• Quick Start
• Fine-tuning
• Performance Leaderboard
• RL Fine-tuning Results
• License
• Acknowledgement
• Citation

BesiegeField is a cutting-edge framework that enables Large Language Models (LLMs) to autonomously design and build complex machines in the Besiege physics-based game environment. This project bridges AI reasoning with creative engineering tasks.

Step 1: Purchase the official copy on Steam

Step 2: Download DepotDownloader

Step 3: Download Besiege v1.60-22044

./DepotDownloader -app 346010 -depot 346016 -manifest 2732248020700221971 \
  -username <steam_user> -password <password>

Step 4: Download v1.20-17395 executables (required for headless operation)

./DepotDownloader -app 346010 -depot 346016 -manifest 5506301120812842666 \
  -username <steam_user> -password <password>

💡 Tip: Find other manifests on SteamDB if needed.

📥 BesiegeField Plugin (Google Drive)

Standard Installation:

sudo apt install mono-complete xvfb  # xvfb only for headless workstation
mono --version  # Verify ≥ 6.8.0.105

# Install mono
cd /path/to/tar
tar -xzf mono-complete-offline.tar.gz
for deb in *.deb; do dpkg -x "$deb" .; done
export PATH="/path/to/mono/usr/bin:$PATH"
export LD_LIBRARY_PATH="/path/to/mono/usr/lib:$LD_LIBRARY_PATH"
export PKG_CONFIG_PATH="/path/to/mono/usr/lib/pkgconfig:$PKG_CONFIG_PATH"
# Make permanent
cat >> ~/.bashrc <<EOF
export PATH="/path/to/mono/usr/bin:\$PATH"
export LD_LIBRARY_PATH="/path/to/mono/usr/lib:\$LD_LIBRARY_PATH"
export PKG_CONFIG_PATH="/path/to/mono/usr/lib/pkgconfig:\$PKG_CONFIG_PATH"
EOF
source ~/.bashrc
# Install xvfb
cd /path/to/xvfb
tar -xzf xvfb-offline.tar.gz
dpkg -i *.deb

Step 1: Extract the plugin archive and copy all files into the v1.60-22044 game folder

Step 2: Copy Besiege.x86 & Besiege.x86_64 from v1.20-17395 into v1.60-22044, overwriting the originals

⚠️ Warning: This enables headless/code control but makes normal GUI start unstable. Keep a backup if you want to launch v1.60 visually.

Step 3: Set permissions

chmod -R 777 /path/to/Besiege

Step 4: Test the vanilla game (use backup copy)

cd /path/to/backup/Besiege && ./run.sh

conda env create -f environment_inferenceonly.yaml
conda activate <env_name>

Folder Structure:

your-project/
├── Besiege/                  # Game installation
└── AgenticCodes/             # Framework code

Edit AgenticCodes/config.py:

Design a machine to throw projectiles:

python main.py \
  -use_model deepseek-chat \
  -task catapult/catapult_level1 \
  -env_num 2 \
  -user_input "Design a machine to throw a boulder (type id 36) in a parabolic trajectory."

Design a machine to move forward:

python main.py \
  -use_model deepseek-chat \
  -task car/car_level1 \
  -env_num 2 \
  -user_input "Design a machine to move forward on a straight road."

Explore all available tasks in environments/env_files/level_menus.json

1. Generated .bsg machine files appear in DEFAULT_SAVE_ROOT
2. Copy them to Besiege/Besiege_Data/SavedMachines
3. Run ./run.sh to launch the game
4. Inspect and test your AI-designed machines in-game!

Add training-related packages:

conda activate <env_name>
pip install -r requirements_rl.txt

cd PostTraining/ColdStart
./run_cold_start.sh <model_path>

If you want to try cold start with human dataset (Not Recommended), you can run with:

cd PostTraining/ColdStart
./run_cold_start.sh <model_path> true

Fill the paths in merge_ckpts.py before running:

python merge_ckpts.py

Configure rl_config.yaml with your settings (important!), then run:

cd PostTraining/RL
./rl_single_agent_light.sh

Performance metrics across different models and methods:

Performance metrics across different models and methods:

Performance comparison of Qwen2.5-14B-Instruct model with different training strategies:

If you find this repository useful for your research or projects, please consider citing our work:

@article{zhang2025besiegefield,
  title={Agentic Design of Compositional Machines},
  author={Zhang, Wenqian and Liu, Weiyang and Liu, Zhen},
  journal={arXiv preprint arXiv:2510.14980},
  year={2025}
}

This project is licensed under the MIT License - see the LICENSE file for details.

We’d like to thank the developers of Besiege for creating such an inspiring game and for nurturing such a vibrant player community — without them, this project wouldn’t exist.

Big thanks also to the BepInEx team for their amazing modding framework, which made it possible for us to push the boundaries of what’s possible in Besiege.

If you find this project helpful, please consider giving it a star! ⭐

This project is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License - see the LICENSE file for details.