Pith. sign in

REVIEW 6 cited by

LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.18354 v2 pith:5LYGAKK4 submitted 2023-05-26 cs.CL cs.AI

classification cs.CLcs.AI
keywords reasoningd-arcgpt-4object-basedtasksabilityabstractabstraction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Can a Large Language Model (LLM) solve simple abstract reasoning problems? We explore this broad question through a systematic analysis of GPT on the Abstraction and Reasoning Corpus (ARC), a representative benchmark of abstract reasoning ability from limited examples in which solutions require some "core knowledge" of concepts such as objects, goal states, counting, and basic geometry. GPT-4 solves only 13/50 of the most straightforward ARC tasks when using textual encodings for their two-dimensional input-output grids. Our failure analysis reveals that GPT-4's capacity to identify objects and reason about them is significantly influenced by the sequential nature of the text that represents an object within a text encoding of a task. To test this hypothesis, we design a new benchmark, the 1D-ARC, which consists of one-dimensional (array-like) tasks that are more conducive to GPT-based reasoning, and where it indeed performs better than on the (2D) ARC. To alleviate this issue, we propose an object-based representation that is obtained through an external tool, resulting in nearly doubling the performance on solved ARC tasks and near-perfect scores on the easier 1D-ARC. Although the state-of-the-art GPT-4 is unable to "reason" perfectly within non-language domains such as the 1D-ARC or a simple ARC subset, our study reveals that the use of object-based representations can significantly improve its reasoning ability. Visualizations, GPT logs, and data are available at https://khalil-research.github.io/LLM4ARC.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction

    cs.AI 2025-08 conditional novelty 6.0 of 10

    On 100 list-function tasks, LLM hypothesis search approaches human-level acquisition (0.487 vs 0.521 mean test accuracy) and clearly beats direct program generation (0.359), with hypothesis generation as the main erro...

  2. EXP-Bench: Can AI Conduct AI Research Experiments?

    cs.AI 2025-05 conditional novelty 6.0 of 10

    EXP-Bench is a new benchmark of 461 end-to-end AI research experiments, and leading AI agents complete fewer than 1 percent of them successfully.

  3. cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending

    cs.LG 2025-08 reject novelty 5.0 of 10

    cMALC-D uses an LLM to generate training contexts for multi-agent RL and a diversity-blending mechanism to avoid mode collapse, claiming improved generalization on traffic signal control.

  4. Reasoning Can Hurt the Inductive Abilities of Large Language Models

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Chain-of-thought reasoning can hurt LLMs' ability to infer hidden rules from gameplay transcripts, and structured interventions recover the lost accuracy.

  5. From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark

    cs.AI 2025-05 conditional novelty 5.0 of 10

    A staged knowledge-prompting method (KAAR) improves LLM test accuracy on ARC by about 5 absolute points over repeated-sampling plan-guided code generation, reaching 35% with GPT-o3-mini.

  6. The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

    cs.CL 2025-02 conditional novelty 5.0 of 10

    A new grid-based benchmark, PhysiCo, shows LLMs can recall and describe physical concepts in text yet lag humans by about 40% when the same concepts are presented as abstract grid transformations.

Pith tools