Tagged articles

CodeAct

2 articles · Page 1 of 1

Jun 24, 2026 · Artificial Intelligence

LLM Agent Design Patterns: From ReAct to Multi‑Agent Collaboration

This article systematically reviews major LLM agent design patterns—including ReAct, CodeAct, static and dynamic planning, reflection, and human‑in‑the‑loop—detailing their core loops, code structures, trade‑offs, and practical use‑cases, and provides a decision tree to help developers choose the most suitable pattern for their tasks.

AgentCodeActLLM

0 likes · 37 min read

LLM Agent Design Patterns: From ReAct to Multi‑Agent Collaboration

Xiaolong Cloud Tech Team

Dec 16, 2025 · Artificial Intelligence

Why Anthropic’s Shift Back to Code Execution Validates the AiPy Python‑Use Paradigm

The article examines Anthropic’s evolution from MCP to Programmatic Tool Calling and its recent return to code execution, contrasting it with the author’s Python‑use (AiPy) paradigm, and analyzes the trade‑offs, reliability versus creativity, and implementation details such as Function Calling, CodeAct, and plugin support.

AI AgentsAnthropicCodeAct

0 likes · 17 min read

Why Anthropic’s Shift Back to Code Execution Validates the AiPy Python‑Use Paradigm