by tobeatraceur · Agent Tool · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Embodied LLM Agents Learn to Cooperate in Organized Teams Source codes for the paper: Guo, Xudong, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L. Griffiths, and Mengdi Wang: Embodied LLM Agents Learn to Cooperate in Organized Teams Paper Website In this repo, we implement embodied and organized multi-LLM-agent teams in the environment VirtualHome to cooperate on household tasks. The agents can make decisions and communicate freely with each other based on LLMs. The codes support multi-agent communication (3 agents) such as broadcasting, keeping silent, and selecting receivers to send distinct messages. Thanks to the flexible communication protocol, the organizational structures can be updated accordingly and autonomously by editing the organization prompts. The agents show emergent cooperative behaviors such as information sharing, leadership & assistance, and requests for guidance. To improve the organization prompts, we propose the Criticize-Reflect architecture based on LLMs to analyze the trajectories and reflect on the feedback to generate novel prompts. Installation Clone the [VirtualHome API](https://github.co
| Stars | 50 |
| Forks | 7 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 60.8630770422065/100 |
| Open Issues | 2 |
| Last Updated | 2025-06-11 |
| Created | 2024-04-23 |
| Platforms | python |
| Est. Tokens | ~6613k |
Explore other popular agent tool tools:
Organized-LLM-Agents is Embodied and organized multi-LLM-agent teams supporting communication for >3 agents. Source codes for the paper "Embodied LLM Agents Learn to Cooperate in Organized Teams".. It is categorized as a Agent Tool with 50 GitHub stars.
Organized-LLM-Agents is primarily written in Python.
You can find installation instructions and usage details in the Organized-LLM-Agents GitHub repository at github.com/tobeatraceur/Organized-LLM-Agents. The project has 50 stars and 7 forks, indicating an active community.