Agentic AI Reference Architecture

Memory · Data store

MCTS Search Tree Store

Data storeMemoryCognition & Memoryarc:MCTSSearchTreeStore

Working-memory store of an MCTS search tree whose nodes are states and edges actions, holding per state-action pair the visit count N(s,a), cumulative reward Q(s,a) and child pointers.

Responsibility. Retains accumulated simulation statistics that guide subsequent search iterations.

Also known as: Search tree, MCTS tree

Variant of Working Memory Buffer abstract

is read by; is written byis monitored byspecializesis written byMCTS Planner: is read by; is written byMCTS PlannerMetrics Collector: is monitored byMetrics CollectorWorking Memory Buffer: specializesWorking Memory BufferSearch Tree Pruner: is written bySearch Tree Pruner
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

is written by dependency

is monitored by assurance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Patterns
Incremental asymmetric tree growthTree reuse across sequential decisions
Risks mitigated
Redundant re-simulation across sequential decisions

Sources

  1. 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.