Cognition · Software component

Flat Planner

Software componentCognitionCognition & Memoryarc:FlatPlanner

A task planner that treats every action as equally fundamental and searches sequences of primitive actions, typically under STRIPS/PDDL precondition-effect semantics, without intermediate abstract tasks.

Responsibility. Generates plans as orderings of primitive actions over the full action space.

Also known as: Flat sequential planner, Classical planner, Classical state-space planner

Variant of Task Planner abstract

When to choose. Choose for simple sequential workflows (3-10 steps) or optimization-dominant problems where provably optimal solutions matter more than fast feasible plans and the action space is small.

Direct neighbourhood (hover for relationship types)

Relationships

reads dependency

Action Effect Model Ch5.4

receives delegation from dependency

HTN Planner Ch5.4

alternative to variability

Design guidance

SHOULD be preferred for simple sequential workflows with few tasks and minimal branching.
MAY be used for primitive-level details beneath a hierarchical backbone.

Quantitative guidance

As stated by the sources; verify before use.

Search space is factorial in the number of primitive actions (e.g., 500 actions for a two-week trip) (Ch5.4).

Classification

Patterns: Flat sequential planningClassical planning (STRIPS/PDDL)Full search-space exploration
Quality attributes: Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Maintainability (ISO/IEC 25010)
Risks mitigated: Hierarchy overhead on simple tasksMissed globally optimal solutions that cross the imposed hierarchy

Sources

Ch5.4: T. Nguyen, "Hierarchical Planning Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.4. ISBN: 9798244538229.