Imagen de Portada

An Analysis of Architectural Impact on LLM-based Abstract Visual Reasoning: A Systematic Benchmark on RAVEN-FAIR

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Urgun, Sinan, Arı, Seçkin
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning
por: Małkiński, Mikołaj, et al.
Publicado: (2024)

I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models
por: Camposampiero, Giacomo, et al.
Publicado: (2025)

Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning
por: Urgun, Dogan, et al.
Publicado: (2026)

Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures
por: Hersche, Michael, et al.
Publicado: (2024)

ACCESS : A Benchmark for Abstract Causal Event Discovery and Reasoning
por: Vo, Vy, et al.
Publicado: (2025)

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

GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
por: Peltonen, Saku, et al.
Publicado: (2026)

A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
por: Chen, Jiaqi, et al.
Publicado: (2026)

QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
por: Prakash, Shvetank, et al.
Publicado: (2025)

Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
por: Chen, Sixing, et al.
Publicado: (2026)

A FAIR and Free Prompt-based Research Assistant
por: Shamsabadi, Mahsa, et al.
Publicado: (2024)

A Unified View of Abstract Visual Reasoning Problems
por: Małkiński, Mikołaj, et al.
Publicado: (2024)

A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation
por: Ma, Qingchuan, et al.
Publicado: (2026)

RAVEN: Multitask Retrieval Augmented Vision-Language Learning
por: Rao, Varun Nagaraj, et al.
Publicado: (2024)

VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains
por: Li, Xuzhao, et al.
Publicado: (2025)

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
por: Shi, Fan, et al.
Publicado: (2025)

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
por: Paglieri, Davide, et al.
Publicado: (2024)

RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs
por: Jamwal, Parteek, et al.
Publicado: (2026)

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
por: Ho, Matthew, et al.
Publicado: (2025)

Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture
por: Sun, Zhong-Hua, et al.
Publicado: (2025)

RAVEN: An Agentic Framework for Multimodal Entity Discovery from Large-Scale Video Collections
por: Rosa, Kevin Dela
Publicado: (2025)

Managing FAIR Knowledge Graphs as Polyglot Data End Points: A Benchmark based on the rdf2pg Framework and Plant Biology Data
por: Brandizi, Marco, et al.
Publicado: (2025)

Watson & Holmes: A Naturalistic Benchmark for Comparing Human and LLM Reasoning
por: Leelawat, Thatchawin, et al.
Publicado: (2026)

RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models
por: Huang, Jie, et al.
Publicado: (2023)

On Data Synthesis and Post-training for Visual Abstract Reasoning
por: Zhu, Ke, et al.
Publicado: (2025)

Multi-Label Contrastive Learning for Abstract Visual Reasoning
por: Małkiński, Mikołaj, et al.
Publicado: (2020)

Learning Differentiable Logic Programs for Abstract Visual Reasoning
por: Shindo, Hikaru, et al.
Publicado: (2023)

Supported Abstract Argumentation for Case-Based Reasoning
por: Gould, Adam, et al.
Publicado: (2025)

ConstraintBench: Benchmarking LLM Constraint Reasoning on Direct Optimization
por: Tso, Joseph, et al.
Publicado: (2026)

ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning
por: Potamitis, Nearchos, et al.
Publicado: (2025)

A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoning
por: Do, Quan, et al.
Publicado: (2024)

MORABLES: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fables
por: Marcuzzo, Matteo, et al.
Publicado: (2025)

On the Step Length Confounding in LLM Reasoning Data Selection
por: Wang, Bing, et al.
Publicado: (2026)

Learning Visual Abstract Reasoning through Dual-Stream Networks
por: Zhao, Kai, et al.
Publicado: (2024)

Symbolic Grounding Reveals Representational Bottlenecks in Abstract Visual Reasoning
por: Vaishnav, Mohit, et al.
Publicado: (2026)

Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
por: Mao, Nathan, et al.
Publicado: (2026)

A Novel Architecture for Symbolic Reasoning with Decision Trees and LLM Agents
por: Kiruluta, Andrew
Publicado: (2025)

Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding
por: Wu, Di, et al.
Publicado: (2025)

ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving
por: Kim, Sejin, et al.
Publicado: (2025)

Thinking with Constructions: A Benchmark and Policy Optimization for Visual-Text Interleaved Geometric Reasoning
por: Zhao, Haokun, et al.
Publicado: (2026)