It has a goal or set of goals that it actively pursues. A goal-based agent has a representation of the current state of the environment and how that environment generally works.

It pursues basic policies or goals that may not be immediately attainable.

These agents consider different scenarios before acting on their environments, to see which action will probably attain a goal.

This consideration of different scenarios is called search and planning. It makes the agent proactive, not just reactive.

Another interesting feature of the goal-based agent is that it already has some model of how the objects in its environment usually behave, so it can perform searches and identify plans based on this knowledge about the world.

Among the actions that can occur in the world are the agent's own actions. So the agent's own possible actions are among the factors that will determine possible future scenarios.