Agentic AI Reference Architecture

Cognition · Data store

World Model State

Data storeCognitionCognition & Memoryarc:WorldModelState

The agent's current structured model of its environment produced by perception, used to understand present state and predict future scenarios.

Responsibility. Holds the agent's current perceived environment state.

Also known as: World model, Unified environmental model, Planning world state, Preconditions/effects state, MCTS root state, Believed state, Internal world model, RL state observation

is read by; is written byis read byis written byis read byis read byis read byis written byis read byis read byis read byis read byis written byis read byis read byis read byis written byState Abstraction Mapper: is read by; is written byState Abstraction MapperAgent Controller: is read byAgent ControllerState-Graph Orchestrator: is written byState-Graph OrchestratorDecision Engine: is read byDecision EngineTask Planner: is read byTask PlannerReplanner: is read byReplannerPlan Executor: is written byPlan ExecutorHTN Planner: is read byHTN PlannerMCTS Planner: is read byMCTS PlannerPlan Deviation Monitor: is read byPlan Deviation MonitorRule Constraint Filter: is read byRule Constraint FilterMultimodal Fusion Engine: is written byMultimodal Fusion EngineOutcome Probability Estimator: is read byOutcome Probability Esti…Reactive Planner: is read byReactive PlannerEdge Cost Updater: is read byEdge Cost UpdaterMarkov State Augmenter: is written byMarkov State Augmenter
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)

Sources

  1. Ch1.4: T. Nguyen, "Memory and Perception Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.4. ISBN: 9798244538229.
  2. 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.
  3. 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.
  4. 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.
  5. Ch5.10: T. Nguyen, "Utility-Based Decision Making Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.10. ISBN: 9798244538229.
  6. Ch5.12: T. Nguyen, "Learning-Based Decision Making Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.12. ISBN: 9798244538229.
  7. Ch5.13: T. Nguyen, "Hybrid Decision Systems Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.13. ISBN: 9798244538229.