Artificial Open World for Evaluating AGI: a Conceptual Design

TL;DR

This paper introduces the concept of an Artificial Open World designed to evaluate AGI by avoiding developer bias and ensuring the agent encounters truly novel problems, with a focus on conceptual design and future formalization.

Contribution

It proposes a novel evaluation framework called Artificial Open World that aims to better assess AGI by preventing developer influence and promoting genuine novelty in problem-solving.

Findings

Conceptual framework for Artificial Open World proposed

A metric for measuring AGI progress introduced

Design principles to ensure world openness discussed

Abstract

How to evaluate Artificial General Intelligence (AGI) is a critical problem that is discussed and unsolved for a long period. In the research of narrow AI, this seems not a severe problem, since researchers in that field focus on some specific problems as well as one or some aspects of cognition, and the criteria for evaluation are explicitly defined. By contrast, an AGI agent should solve problems that are never-encountered by both agents and developers. However, once a developer tests and debugs the agent with a problem, the never-encountered problem becomes the encountered problem, as a result, the problem is solved by the developers to some extent, exploiting their experience, rather than the agents. This conflict, as we call the trap of developers' experience, leads to that this kind of problems is probably hard to become an acknowledged criterion. In this paper, we propose an evaluation method named Artificial Open World, aiming to jump out of the trap. The intuition is that most of the experience in the actual world should not be necessary to be applied to the artificial world, and the world should be open in some sense, such that developers are unable to perceive the world and solve problems by themselves before testing, though after that they are allowed to check all the data. The world is generated in a similar way as the actual world, and a general form of problems is proposed. A metric is proposed aiming to quantify the progress of research. This paper describes the conceptual design of the Artificial Open World, though the formalization and the implementation are left to the future.