Abstract
For over sixty years, the artificial intelligence and cognitive
systems communities have represented problems to be solved as a
combination of an initial and goal state along with some background
domain knowledge. In this paper, I challenge this representation
because it does not adequately capture the nature of a problem.
Instead, a problem is a state of the world that limits choice in terms
of potential goals or available actions. To capture this view of a
problem, a representation should include a characterization of the
context that exists when a problem arises and an explanation that
causally links the part of the context that contributes to the problem
with a goal whose achievement constitutes a solution. The challenge to
the research community is not only to represent such features but to
design and implement agents that can infer them autonomously.
