Cover Image

Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Task

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Junjie, Yu, Mo, Liu, Lemao, Yeung, Dit-Yan, Zhou, Jie
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models
by: Chung, Tsz Ting, et al.
Published: (2025)

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
by: Yu, Mo, et al.
Published: (2025)

Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability
by: Chung, Tsz Ting, et al.
Published: (2024)

Rethinking Targeted Adversarial Attacks For Neural Machine Translation
by: Wu, Junjie, et al.
Published: (2024)

Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models
by: Wu, Junjie, et al.
Published: (2024)

SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension
by: Wu, Junjie, et al.
Published: (2025)

Towards Threshold-Free KV Cache Pruning
by: Ni, Xuanfan, et al.
Published: (2025)

ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGI
by: Lehmann, Jens, et al.
Published: (2026)

Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks
by: Rudakov, Evgenii, et al.
Published: (2025)

ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
by: Foundation, ARC Prize
Published: (2026)

G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o
by: Tong, Tony Cheng, et al.
Published: (2024)

Large Language Models Can Self-Improve in Long-context Reasoning
by: Li, Siheng, et al.
Published: (2024)

Towards Privacy-Preserving Machine Translation at the Inference Stage: A New Task and Benchmark
by: Shao, Wei, et al.
Published: (2026)

From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark
by: Lei, Chao, et al.
Published: (2025)

InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context
by: Liu, Ziyi, et al.
Published: (2024)

Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
by: Fu, Tingchen, et al.
Published: (2024)

LLM-ARC: Enhancing LLMs with an Automated Reasoning Critic
by: Kalyanpur, Aditya, et al.
Published: (2024)

Compositional-ARC: Assessing Systematic Generalization in Abstract Spatial Reasoning
by: Mondorf, Philipp, et al.
Published: (2025)

Impact of Noise on LLM-Models Performance in Abstraction and Reasoning Corpus (ARC) Tasks with Model Temperature Considerations
by: Khandalkar, Nikhil, et al.
Published: (2025)

ARC Prize 2025: Technical Report
by: Chollet, François, et al.
Published: (2026)

ARC Prize 2024: Technical Report
by: Chollet, Francois, et al.
Published: (2024)

ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
by: Romeo, Carlo, et al.
Published: (2026)

Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective
by: Franzen, Daniel, et al.
Published: (2025)

Can Complexity and Uncomputability Explain Intelligence? SuperARC: A Test for Artificial Super Intelligence Based on Recursive Compression
by: Hernández-Espinosa, Alberto, et al.
Published: (2025)

Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
by: Qiu, Yu-Ning, et al.
Published: (2026)

AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
by: Zhang, Jiaming, et al.
Published: (2024)

MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
by: Zhang, Jiaming, et al.
Published: (2023)

MagicDrive: Street View Generation with Diverse 3D Geometry Control
by: Gao, Ruiyuan, et al.
Published: (2023)

GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
by: Chen, Kai, et al.
Published: (2023)

NICE: A Theory-Grounded Diagnostic Benchmark for Social Intelligence of LLMs
by: Qi, Yunjin, et al.
Published: (2026)

Multi-Perspective Transformers in ARC-AGI-2 Challenge
by: Talley, Caleb, et al.
Published: (2026)

A Survey on the Honesty of Large Language Models
by: Li, Siheng, et al.
Published: (2024)

Can LLMs Understand Social Norms in Autonomous Driving Games?
by: Wang, Boxuan, et al.
Published: (2024)

A Decomposition Perspective to Long-context Reasoning for LLMs
by: Xiao, Yanling, et al.
Published: (2026)

The role of positional encodings in the ARC benchmark
by: Costa, Guilherme H. Bandeira, et al.
Published: (2025)

NSA: Neuro-symbolic ARC Challenge
by: Batorski, Paweł, et al.
Published: (2025)

Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation
by: Yang, Yue, et al.
Published: (2025)

ARC-AGI-2 Technical Report
by: de Oliveira, Wallyson Lemes, et al.
Published: (2026)

TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models
by: Li, Pengxiang, et al.
Published: (2023)

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
by: Chen, Jingxiang, et al.
Published: (2026)