Cognition · Software component
Replanner
Software componentCognitionCognition & MemoryVariation point (abstract)arc:Replanner
A component that revises the current plan from execution error observations, e.g., inserting retries, substituting cached sources, or reordering steps.
Responsibility. Revises plans on failure or new information.
Also known as: Dynamic replanning, Hierarchical replanner, Local repair, Replanning strategy, Adaptive replanner, Strategic replanner
Variants
| Variant | When to choose |
|---|---|
| Complete Replanner | Choose when failures are global or rare (<10% of executions), unpredictable, memory is constrained, spaces are small, latency can be tolerated, or optimality matters more than continuity. |
| Contingency Branch Activator | Choose when failures are frequent (>30%), predictable from observable conditions (time of day, sensor state), stable, few (2-5 modes), and replanning pauses of 3-5 s are intolerable. |
| Incremental Search Replanner | Choose when changes are frequent but localized edge-cost modifications on a stable topology, state spaces are large, memory permits search-tree persistence, and optimal solutions matter. |
| Plan Repairer | Choose when discrepancies are localized, adaptation must be fast, and plan stability matters (multi-robot committed trajectories, user-communicated ETAs); good-enough solutions suffice. |
Relationships
invokes dependency
is invoked by dependency
reads dependency
writes dependency
- Execution Plan abstract Ch1.2 Ch5.6
- Task Network Ch5.4
- Working Memory Buffer abstract Ch1.5A Ch1.6
is routed to by dynamic
- Transition Router abstract Ch1.6
is triggered by dynamic
triggers dynamic
is constrained by control
is orchestrated by control
Design guidance
- SHOULD bound replanning frequency since each cycle adds LLM cost and delay.
- SHOULD be reached by conditional routing when failed actions write error information into state.
- SHOULD replan from the abstraction level where assumptions failed rather than from the root goal.
- SHOULD combine strategies: contingencies for the most common failure modes, incremental replanning for localized changes, and complete replanning as a fallback for rare global disruptions.
- SHOULD generate the new plan from the current actual state, not the originally predicted state.
Classification
- Patterns
- Dynamic replanningPlan-and-ExecuteReplanningContinual replanningHierarchical replanningLocal repair at parent abstract taskProgressive deepeningReactive replanningDeliberative replanningMulti-layered (hybrid) replanning
- Quality attributes
- Flexibility (ISO/IEC 25010)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
- Risks mitigated
- Plan rigidityExecuting obsolete instructionsExecution of an invalid planUnexpected obstacles during web navigationItems going out of stock mid-sessionPlan invalidation by exogenous eventsCascading action failures from unmet preconditionsGoal obsolescence
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.
- 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.
- Ch3.6: T. Nguyen, "Trace Analysis and Execution Debugging," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.6. 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.
- Ch5.6: 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.
- 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.