Planning Loops and State Graphs

Key jargon

Term	Plain-language meaning
Plan	A proposed sequence or dependency structure for reaching a goal.
State graph	Nodes and transitions representing allowed workflow states.
Transition	A validated move from one state to another.
Stopping condition	A rule that ends or escalates a loop.

Key concepts

A plan is a hypothesis that must adapt to observations; it is not proof that steps will succeed.
State graphs make legal transitions, retries, approvals, and terminal states explicit.

Concept map

flowchart LR
    A["Create bounded plan"] --> B["Execute current node"]
    B --> C["Observe and update state"]
    C --> D["Stop revise or escalate"]

A loop repeats “observe → decide → act → evaluate.” A graph makes allowed states and transitions explicit. The loop is behavior; the graph is control and memory.

Minimum bounded loop

goal → plan → execute one bounded step → observe → verify
                               ├── done
                               ├── revise within budget
                               ├── request approval/input
                               └── stop safely

Required brakes

Maximum steps, time, tokens, cost, and tool effects.
No-progress and repeated-failure detection.
Explicit done/blocked assertions.
Checkpoint and resume contract.
Human gate before scope expansion or consequential effect.
Evidence required before a success claim.

Exercise

Create states for a research agent: intake, search, source review, draft, fact check, revision, complete, and blocked. List allowed transitions and a stop condition for each active state.

Research boundary

Planning methods such as tree search, reflection, and test-time scaling can improve some tasks but add inference cost and do not guarantee truth or safe action.