# System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI

arXiv: https://arxiv.org/abs/2410.07866 · HTML: https://mlsanity.com/paper/2410.07866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 18 of 18)

- [Large Language Models as General Pattern Machines](https://mlsanity.com/paper/2307.04721/) (2023)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations](https://mlsanity.com/paper/2305.18354/) (2023)
- [Thinking Fast and Slow in AI](https://mlsanity.com/paper/2010.06002/) (2020)
- [Code Repair with LLMs gives an Exploration-Exploitation Tradeoff](https://mlsanity.com/paper/2405.17503/) (2024)
- [Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2210.09880/) (2022)
- [Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2403.11793/) (2024)
- [Neural-guided, Bidirectional Program Search for Abstraction and Reasoning](https://mlsanity.com/paper/2110.11536/) (2021)
- [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)
- [Counting and Algorithmic Generalization with Transformers](https://mlsanity.com/paper/2310.08661/) (2023)
- [Generalized Planning for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2401.07426/) (2024)
- [A Neurodiversity-Inspired Solver for the Abstraction & Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis](https://mlsanity.com/paper/2302.09425/) (2023)
- [Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle](https://mlsanity.com/paper/2311.00545/) (2023)
- [Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning](https://mlsanity.com/paper/2306.03175/) (2023)
- [Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models](https://mlsanity.com/paper/2401.11725/) (2024)
- [Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2405.06399/) (2024)
- [Fast Analysis of the OpenAI O1-Preview Model in Solving Random K-SAT Problem: Does the LLM Solve the Problem Itself or Call an External SAT Solver?](https://mlsanity.com/paper/2409.11232/) (2024)

## Abstract (arXiv)

Despite their broad applicability, transformer-based models still fall short in System~2 reasoning, lacking the generality and adaptivity needed for human--AI alignment. We examine weaknesses on ARC-AGI tasks, revealing gaps in compositional generalization and novel-rule adaptation, and argue that closing these gaps requires overhauling the reasoning pipeline and its evaluation. We propose three research axes: (1) Symbolic representation pipeline for compositional generality, (2) Interactive feedback-driven reasoning loop for adaptivity, and (3) Test-time task augmentation balancing both qualities. Finally, we demonstrate how ARC-AGI's evaluation suite can be adapted to track progress in symbolic generality, feedback-driven adaptivity, and task-level robustness, thereby guiding future work on robust human--AI alignment.