When implementing stateful orchestration for agentic workflows using LangGraph, which memory management approach provides the...

This lines up with NVIDIA guidance because long-running agents should retrieve compact relevant context instead of replaying the entire conversation history into every call. A session-ID checkpointer persists exactly the state the graph needs. Full-history memory is too expensive; fixed windows can drop critical state. Option C fits the operating model because the problem describes an agent that must remain adaptive under changing inputs and infrastructure conditions. The selected option specifically C states “Use session-ID based checkpointer with user-defined schema for selective state persistence”, which matches the operational requirement rather than a superficial wording match. The durable control mechanism is checkpointed state keyed by session or user, with schemas that preserve only the fields the workflow needs later. The losing choices mostly optimize for short-term convenience; unbounded memory creates privacy, relevance, and performance problems unless persistence is deliberate. For certification purposes, read the question as asking for controlled autonomy, not raw LLM creativity. The memory policy should define what is persisted, what is summarized, and what is discarded to avoid both context loss and prompt bloat.