Agentic AI Reference Architecture

Cognition · Software component

LLM Task Planner

Software componentCognitionCognition & Memoryarc:LLMTaskPlanner

A task planner that prompts a language model to break a goal into subgoals and select available functions for each, leveraging broad model knowledge rather than an encoded method library.

Responsibility. Produces shallow goal decompositions and function selections using LLM reasoning.

Also known as: Semantic Kernel planner, LLM-based goal decomposer

Variant of Task Planner abstract

When to choose. Choose for high-level decomposition of open-ended goals where broad knowledge matters and encoding deep domain methods in prompts would be too expensive.

delegates to; is target of alternativeToinvokesspecializesis configured bywritesis configured byreadsis invoked byHTN Planner: delegates to; is target of alternativeToHTN PlannerLLM Inference Service: invokesLLM Inference ServiceTask Planner: specializesTask PlannerPrompt Exemplar Set: is configured byPrompt Exemplar SetExecution Plan: writesExecution PlanSystem Prompt Template: is configured bySystem Prompt TemplateTool Registry: readsTool RegistryPlugin Kernel Orchestrator: is invoked byPlugin Kernel Orchestrator
Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

delegates to dependency

invokes dependency

is invoked by dependency

reads dependency

writes dependency

alternative to variability

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Patterns
LLM-driven goal decompositionHybrid LLM high-level / HTN operational planning
Technologies
Semantic Kernel
Quality attributes
Flexibility (ISO/IEC 25010)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Multi-step workflows exceeding single-LLM-call capacityWrong tool selectionIncorrect step ordering

Sources

  1. 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.
  2. Ch8.2A: T. Nguyen, "Error Rates and Reliability," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.2A. ISBN: 9798244538229.