Cognition · Software component

Task Planner

Software componentCognitionCognition & MemoryVariation point (abstract)arc:TaskPlanner

A cognition component that decomposes a high-level goal into a concrete ordered set of executable steps before execution begins.

Responsibility. Decomposes goals into executable plans.

Also known as: Planner, Web action sequence planner, Agent-oriented task decomposer, Planning component, Initial planner, Path planner

Direct neighbourhood (hover for relationship types)

Variants

Variant	When to choose
Contingency Planner	—
Flat Planner	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.
Graph Search Planner abstract	—
HTN Planner	Choose when the goal has naturally nested structure, reusable decomposition patterns exist, stakeholders need multiple abstraction views, or staged commitment under uncertainty is needed, and the world is stable during planning.
LLM Task Planner	Choose for high-level decomposition of open-ended goals where broad knowledge matters and encoding deep domain methods in prompts would be too expensive.
MCTS Planner	Choose when heuristics are hard to design, the state space is enormous, near-optimal solutions are acceptable for faster computation, transitions are stochastic or partially observable, or asymmetric tree growth pays off (game playing, robotic task planning, chemical retrosynthesis, navigation among dynamic crowds).
Monte Carlo Planner	Choose for one-shot planning problems with expensive forward-model simulations (e.g., computationally intensive physics), where lower memory use outweighs MCTS's progressive statistical refinement.
Reactive Planner	Choose for highly dynamic domains where strategic decisions become invalid before tactical decomposition finishes, or where problem structure is undefined.

Relationships

is configured by structural

Action Effect Model Ch5.6

invokes dependency

LLM Inference Service Ch1.2
Thought Exploration Controller abstract Ch5.2

is invoked by dependency

reads dependency

is orchestrated by control

produces lifecycle

Execution Plan abstract Ch4.7

Design guidance

SHOULD NOT produce excessively detailed plans with redundant steps or circular dependencies.
SHOULD plan only subtasks the executor has tools to fulfil.
MAY keep lean state (plan plus current step results) to reduce context consumption, at the cost of detailed history for mid-execution replanning.
SHOULD maintain the goal hierarchy (goals, subgoals, achieved and pending) in workflow state.
MUST map every subtask to an available agent or tool capability at an executable granularity (solvability).
MUST cover every aspect of the original query, including implicit prerequisite steps (completeness).
SHOULD eliminate overlapping subtasks by making shared data needs explicit dependencies (non-redundancy).
MUST specify dependencies so independent subtasks run in parallel and dependent ones wait for required outputs.
SHOULD own task decomposition, dependency tracking and resource allocation, delegating only exploration of alternative approaches at decision points to tree search.
SHOULD select the planning approach (hierarchical, flat, reactive, LLM-based) from task structure, stability of the environment and availability of domain decomposition knowledge.
SHOULD record, for every planned action, its preconditions, expected effects and verification conditions so execution can be monitored against testable predictions.

Classification

Patterns: Hierarchical task decompositionPlan-and-ExecuteHierarchical planningMulti-agent collaborative planningDependency traversal ((Task)-[:DEPENDS_ON]->(Task))Upfront trajectory planning with completeness verificationAgent-oriented task decompositionLayered CoT decompositionTree-of-Thought embedded for strategy selection within hierarchical planningGoal decomposition into primitive actionsPlanning under uncertainty with staged commitmentSimulation-based planningPlan-execute-monitor-replan cycleInformed (heuristic) searchHierarchical decomposition
Quality attributes: Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Cost efficiencyPerformance efficiency (ISO/IEC 25010)

Sources

Ch1.2: T. Nguyen, "Core Agent Patterns," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.2. ISBN: 9798244538229.
Ch1.5A: T. Nguyen, "Stateful Orchestration - Introduction and Core Concepts," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.5A. ISBN: 9798244538229.
Ch1.6: T. Nguyen, "Stateful Orchestration - Pitfalls, Integration, and Synthesis," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.6. ISBN: 9798244538229.
Ch1.7B: T. Nguyen, "Relational Reasoning with Knowledge Graphs - Hybrid RAG+KG Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.7B. ISBN: 9798244538229.
Ch3.3: T. Nguyen, "Web Navigation and Interaction Benchmarks," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.3. ISBN: 9798244538229.
Ch3.8: T. Nguyen, "Action Accuracy Metrics," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.8. ISBN: 9798244538229.
Ch4.7: T. Nguyen, "Scaling Strategies," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.7. ISBN: 9798244538229.
Ch5.1: T. Nguyen, "Chain-of-Thought (CoT) Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.1. ISBN: 9798244538229.
Ch5.2: T. Nguyen, "Tree-of-Thought (ToT) Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.2. ISBN: 9798244538229.
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.
Ch5.5: T. Nguyen, "Monte Carlo Tree Search Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.5. ISBN: 9798244538229.
Ch5.6: T. Nguyen, "A* Search and Replaning," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.6. ISBN: 9798244538229.