Executable Code Actions Elicit Better LLM Agents 📃 Paper • 🤗 Data (CodeActInstruct) • 🤗 Model (CodeActAgent-Mistral-7b-v0.1) • 🤖 Chat with CodeActAgent! We propose to use executable code to consolidate LLM agents’ actions into a unified action space (CodeAct). Integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations (e.g., code execution results) through multi-turn interactions (check out this example!).
| Stars | 1,616 |
| Forks | 129 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 41.25/100 |
| Open Issues | 13 |
| Last Updated | 2024-05-23 |
| Created | 2024-01-13 |
| Platforms | python |
| Est. Tokens | ~1639k |
These tools work well together with code-act for enhanced workflows:
Explore other popular ai 工具 tools:
code-act is Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.. It is categorized as a AI 工具 with 1.6k GitHub stars.
code-act is primarily written in Python. It covers topics such as llm, llm-agent, llm-finetuning.
You can find installation instructions and usage details in the code-act GitHub repository at github.com/xingyaoww/code-act. The project has 1.6k stars and 129 forks, indicating an active community.
code-act is released under the MIT license, making it free to use and modify according to the license terms.