Cognition · Data artifact

Task Network

Data artifactCognitionCognition & Memoryarc:TaskNetwork

The evolving hierarchical partial plan: a tree or DAG of abstract and primitive tasks with decomposition edges, ordering constraints, causal links and resource assignments.

Responsibility. Represents the current state of hierarchical decomposition, retaining parent-child structure for repair and multi-level views.

Also known as: Hierarchical task network, Decomposition tree, Partial plan

Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

Plan Constraint Propagator Ch5.4
Replanner abstract Ch5.4

is written by dependency

HTN Planner Ch5.4
Replanner abstract Ch5.4

Design guidance

SHOULD retain the decomposition hierarchy after planning so failure impact scope and local repair points are identifiable.

Classification

Patterns: Task network refinementCausal-link protection
Quality attributes: Explainability (NIST AI RMF: explainable and interpretable)Transparency and accountability (NIST AI RMF: accountable and transparent)
Risks mitigated: Loss of rationale in flat 100-step plansUnclear failure impact scope

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.