Lianhui Qin (@Lianhuiq)
2025-12-01 | โค๏ธ 266 | ๐ 59
๐จ๐จCan agents earn money, run a business, or even self-organize a society in the physical social world? ๐ค๐ค
Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? ๐ถ
Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds.
SimWorld features 3 key designs:
1โฃOpen-ended realistic world simulation
- built on Unreal Engine 5, with accurate physical social dynamics
- 100+ built-in environments (city, island, wilderness โฆ)
- language-controllable procedural generation
- text-to-3D asset generation
2โฃNative interface for LLM/VLM agents
- Gym-like agent-environment interaction APIs
- plug in any LLMs/VLMs (GPTs, Gemini, Qwen โฆ)
- rich multi-modal perception
- open-vocabulary natural-language action outputs
3โฃDiverse physical and social reasoning scenarios
- long-horizon embodied reasoning
- multi-agent collaboration / competition
- easily customizable for any reasoning tasks
SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc.
Project website + more details in the thread๐ โฆ1/
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
