We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents. Using the flexibility of LLMs to be prompted to do various novel tasks using zero-shot, few-shot, context-grounded prompting, we explore the feasibility of using LLMs to solve the ARC Challenge. We firstly convert the input image into multiple suitable text-based abstraction spaces. We then utilise the associative power of LLMs to derive the input-output relationship and map this to actions in the form of a working program, similar to Voyager / Ghost in the MineCraft. In addition, we use iterative environmental feedback in order to guide LLMs to solve the task. Our proposed approach achieves 50 solves out of 111 training set problems (45%) with just three abstraction spaces - grid, object and pixel - and we believe that with more abstraction spaces and learnable actions, we will be able to solve more.

Unfortunately, by using such heuristics, it is not possible to solve any reasonably complex set of problems in a reasonably complex domain. Regardless of how good such heuristics are at directing search, attempts to traverse a complex problem space can be caught in a combinatorial quagmire. This paper presents an approach to augmenting the power of the heuristic search process. The essence of this approach is to utilize a means for discriminating between important information and details in the problem space. By planning in a hierarchy of abstraction spaces in which successive levels of detail are introduced, significant increases in problem-solving power have been achieved. Section II sketches the hierarchical planning approach and gives motivation for its use. Sections III and IV describe the definition and use of abstraction spaces by ABSTRIPS (Abstraction-Based STRIPS), a modification of the STRIPS problem-solving system that incorporates this approach. Section V describes the performance of the system.