HomeResearch LibraryExecutable Code Actions Elicit Better LLM Agents
system architectureChapter 1ICML 2024 · 2024

Executable Code Actions Elicit Better LLM Agents

Xingyao Wang (UIUC), Yangyi Chen (UIUC)

Abstract

We propose CodeAct, an agent design that uses executable Python code as the action space instead of structured JSON actions. CodeAct agents can dynamically create and execute code to interact with environments.

Key Contributions

  • →Code-as-action paradigm
  • →Dynamic tool creation
  • →Improved task completion rates
Eigenvector Commentary

CodeAct is a significant insight: code is a better action representation than JSON because it is composable, debuggable, and expressive. For enterprise agents that need to interact with complex systems, executable code actions dramatically expand the action space.

Topics

code actionsexecutable actionsagent designPython