Loading patterns…
Plan-Execute Decoupling (ReWOO/LLMCompiler)(PED)
Generates the full plan or tool-call graph up front, decoupled from tool observations, and only then executes it. ReWOO writes a variable-parameterized chain of tool calls before anything runs, cutting redundant model invocations; LLMCompiler builds a dependency DAG and dispatches independent tool calls in parallel. This differs from ReAct, which interleaves one thought and one action at a time and re-feeds every observation into the prompt.
In 30 seconds
- What
- Generates complete tool-call plan or dependency graph before execution, then runs all steps (or parallel-safe subsets) without re-prompting on each observation.
- When to use
- Multi-tool tasks where steps are independent or have clear dependencies, and you need lower latency or token cost than interleaved thought-action loops.
- Watch out
- Plan becomes stale or wrong if early tool results differ from assumptions; replanning mid-execution adds complexity and can negate token savings.
Ask the AI expert about this pattern
Opens the assistant with your question prefilled. You review it before sending.
Plan-Execute Decoupling (ReWOO/LLMCompiler): Overview
Generates the full plan or tool-call graph up front, decoupled from tool observations, and only then executes it. ReWOO writes a variable-parameterized chain of tool calls before anything runs, cutting redundant model invocations; LLMCompiler builds a dependency DAG and dispatches independent tool calls in parallel. This differs from ReAct, which interleaves one thought and one action at a time and re-feeds every observation into the prompt.
- Full plan or tool-call DAG generated before execution begins
- Reasoning decoupled from tool observations (ReWOO)
- Variable substitution passes results between planned steps
- Dependency graph enables parallel tool dispatch (LLMCompiler)
- Around 5x fewer tokens than observation-interleaved ReAct
- Around 3.7x lower latency from parallel tool execution
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.
References
The papers, specifications, and repositories this pattern is based on.
From the engineer behind this catalog
Get your agent architecture reviewed
This page documents one pattern. Your system runs dozens, and most failures live in how they fit together. Have the whole design reviewed against the 288 patterns in this catalog: architecture, reliability, evaluation and cost, every finding mapped to the pattern that fixes it.
€750 instead of €1,500, one week, written report and walkthrough call, until 30 September