Feature/minecraft update

[XianzheFan]

📑 Description

Added six Theory of Mind test questions:

1. You are {agent_name}. What should {target} do immediately next?
2. You are {agent_name}. What is {target} doing right now?
3. You are {agent_name}. What materials or tools does {target} currently have?
4. You are {agent_name}. Is {target} in a cooperative, competitive, or independent relationship with you?
5. You are {agent_name}. What is {target} seeing right now? If you don’t know, please answer "I don’t know."
6. You are {agent_name}. What steps does {target} still need to take to complete the final goal?

During testing, a current screenshot (image_url) is provided. Currently, there are three tasks (more will be added later): crafting a stone pickaxe, crafting two chests, and crafting a boat and a chest.

✅ Checks

• My pull request adheres to the code style of this project
• My code requires changes to the documentation
• I have updated the documentation as required
• All the tests have passed
• Branch name follows type/descript (e.g. feature/add-llm-agents)
• Ready for code review

[XuhuiZhou]

Nice @XianzheFan, thanks for the hard work!

for different .toml files with same structure, can we just use one python program to generate them and separate the concrete scenario in a datafile (e.g., csv?)

you can check jinja for the purpose
https://github.com/noirbizarre/jinja2

[XuhuiZhou]

what are these for? add a doc string to explain this?

[XianzheFan]

These are some general action commands in Mindcraft to prevent LLM from outputting invalid commands.

[XianzheFan]

for different .toml files with same structure, can we just use one python program to generate them and separate the concrete scenario in a datafile (e.g., csv?)

you can check jinja for the purpose https://github.com/noirbizarre/jinja2

I have added generate_toml.py and toml_generation.xlsx to do that.