# ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)

arXiv: https://arxiv.org/abs/2412.07322 · HTML: https://mlsanity.com/paper/2412.07322/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 14 of 14)

- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain](https://mlsanity.com/paper/2305.07141/) (2023)
- [LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations](https://mlsanity.com/paper/2305.18354/) (2023)
- [Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks](https://mlsanity.com/paper/2311.09247/) (2023)
- [Communicating Natural Programs to Humans and Machines](https://mlsanity.com/paper/2106.07824/) (2021)
- [Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2210.09880/) (2022)
- [CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay](https://mlsanity.com/paper/2402.04858/) (2024)
- [HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis](https://mlsanity.com/paper/2405.15880/) (2024)
- [Neural networks for abstraction and reasoning: Towards broad generalization in machines](https://mlsanity.com/paper/2402.03507/) (2024)
- [A Neurodiversity-Inspired Solver for the Abstraction & Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis](https://mlsanity.com/paper/2302.09425/) (2023)

## Built on by (most cited first, 8 of 8)

- [Think Visually, Reason Textually: Vision-Language Synergy in ARC](https://mlsanity.com/paper/2511.15703/) (2025)
- [The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning](https://mlsanity.com/paper/2603.13372/) (2026)
- [Slots, Transitions, Loops: Learning Composable World Models for ARC](https://mlsanity.com/paper/2606.12316/) (2026)
- [Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization](https://mlsanity.com/paper/2510.06274/) (2025)
- [TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning](https://mlsanity.com/paper/2607.29586/) (2026)
- [Solomonoff-Inspired Hypothesis Ranking with LLMs for Prediction Under Uncertainty](https://mlsanity.com/paper/2512.17145/) (2025)
- [Narcissus: Program Synthesis Using Context-Aware LLM Approximations](https://mlsanity.com/paper/2608.25657/) (2026)
- [Combining LLMs and Genetic Search for ARC-AGI-2](https://mlsanity.com/paper/2609.27242/) (2026)

## Abstract (arXiv)

The Abstraction and Reasoning Corpus (ARC) poses a significant challenge to artificial intelligence, demanding broad generalization and few-shot learning capabilities that remain elusive for current deep learning methods, including large language models (LLMs). While LLMs excel in program synthesis, their direct application to ARC yields limited success. To address this, we introduce ConceptSearch, a novel function-search algorithm that leverages LLMs for program generation and employs a concept-based scoring method to guide the search efficiently. Unlike simplistic pixel-based metrics like Hamming distance, ConceptSearch evaluates programs on their ability to capture the underlying transformation concept reflected in the input-output examples. We explore three scoring functions: Hamming distance, a CNN-based scoring function, and an LLM-based natural language scoring function. Experimental results demonstrate the effectiveness of ConceptSearch, achieving a significant performance improvement over direct prompting with GPT-4. Moreover, our novel concept-based scoring exhibits up to 30% greater efficiency compared to Hamming distance, measured in terms of the number of iterations required to reach the correct solution. These findings highlight the potential of LLM-driven program search when integrated with concept-based guidance for tackling challenging generalization problems like ARC.