--- title: Plan-then-Execute LLM Agents url: https://www.emergentmind.com/topics/plan-then-execute-llm-agents type: topic --- # Plan-then-Execute LLM Agents A plan-then-execute (PTE) paradigm in LLM agents refers to architectures that decouple high-level planning—producing an explicit, global or hierarchical plan—from the downstream execution of that plan, which is typically handled by a separate module or subagent. This separation is motivated by the need for interpretability, modularity, controllable reasoning, reliability, and the limitations of end-to-end or interleaved planning/acting (e.g., ReAct) protocols in complex, long-horizon, or high-assurance environments. ## 1. Formal Foundations and Core Architecture The canonical PTE agent leverages a two-stage workflow: first, a planner module creates an explicit plan—a sequence (or DAG) of high-level steps or subgoals—based on a user goal or instruction; then, an executor module realizes each step, typically by grounding it to environment actions, tool calls, or subagent invocations. Let \(u\) denote the (possibly natural-language) user instruction. The planner \(\pi_g\) emits a plan \[ p = (s_1, s_2, \dots, s_m)\,,\;\quad s_i \in \text{natural-language subgoal or structured schema}\,. \] For execution, an agent \(\pi_\theta\) is conditioned on both \(u\) and \(p\), producing action sequences: \[ a_t \sim \pi_\theta( \cdot \mid u, p, a_{