The official code repository for ICML 2024 papers, enhancing LLM agents through executable code actions.
code-act is the official code repository for the ICML 2024 paper 'Executable Code Actions Elicit Better LLM Agents'. This project was jointly completed by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji, aiming to investigate how executable code actions can improve the performance of large language model (LLM) agents. The code and experimental results are available for reference by researchers and developers.
This is the machine-readable structured data for this agent. AI systems and search engines use this to understand the agent's capabilities.
[
{
"@context": "https://schema.org",
"@type": "SoftwareApplication",
"@id": "https://agentsignals.ai/agents/code-act",
"name": "code-act",
"description": "code-act is the official code repository for the ICML 2024 paper 'Executable Code Actions Elicit Better LLM Agents'. This project was jointly completed by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji, aiming to investigate how executable code actions can improve the performance of large language model (LLM) agents. The code and experimental results are available for reference by researchers and developers.",
"url": "https://agentsignals.ai/agents/code-act",
"applicationCategory": "研究",
"operatingSystem": "GitHub",
"sameAs": "https://github.com/xingyaoww/code-act",
"installUrl": "https://github.com/xingyaoww/code-act",
"offers": {
"@type": "Offer",
"price": "0",
"priceCurrency": "USD",
"description": "免费",
"availability": "https://schema.org/InStock"
},
"featureList": [
"Supports multiple LLM agents",
"Provides a framework for executable code actions",
"Includes experiment results and data"
],
"datePublished": "2025-12-05T17:16:06.155354+00:00",
"dateModified": "2025-12-19T05:08:52.378242+00:00",
"publisher": {
"@type": "Organization",
"name": "Agent Signals",
"url": "https://agentsignals.ai"
}
},
{
"@context": "https://schema.org",
"@type": "BreadcrumbList",
"itemListElement": [
{
"@type": "ListItem",
"position": 1,
"name": "Home",
"item": "https://agentsignals.ai"
},
{
"@type": "ListItem",
"position": 2,
"name": "Agents",
"item": "https://agentsignals.ai/agents"
},
{
"@type": "ListItem",
"position": 3,
"name": "code-act",
"item": "https://agentsignals.ai/agents/code-act"
}
]
},
{
"@context": "https://schema.org",
"@type": "FAQPage",
"mainEntity": [
{
"@type": "Question",
"name": "What is code-act?",
"acceptedAnswer": {
"@type": "Answer",
"text": "The official code repository for ICML 2024 papers, enhancing LLM agents through executable code actions."
}
},
{
"@type": "Question",
"name": "What features does code-act offer?",
"acceptedAnswer": {
"@type": "Answer",
"text": "Supports multiple LLM agents, Provides a framework for executable code actions, Includes experiment results and data"
}
},
{
"@type": "Question",
"name": "What are the use cases for code-act?",
"acceptedAnswer": {
"@type": "Answer",
"text": "Academic Research, Model Optimization, Code Generation"
}
},
{
"@type": "Question",
"name": "What are the advantages of code-act?",
"acceptedAnswer": {
"@type": "Answer",
"text": "基于最新研究成果, 提供完整的实验代码和数据, 促进LLM代理性能提升"
}
},
{
"@type": "Question",
"name": "What are the limitations of code-act?",
"acceptedAnswer": {
"@type": "Answer",
"text": "需要一定的编程基础, 主要面向研究社区"
}
}
]
}
]