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.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

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.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Key Contributions

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

Topics

code actionsexecutable actionsagent designPython