In the news
Plan-and-Execute Agents
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangChain introduced Plan-and-Execute agents that separate planning from execution, contrasting with previous ReAct-based Action agents.
- Why it matters
- Matters for engineers building complex, long-term agentic systems in production that need better reliability and handling of intricate user objectives.
- Watch out
- Plan-and-Execute agents require significantly more language model calls than Action agents, increasing costs despite potential for smaller model use.
Listen to this summary
- agent
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.