Imagen de Portada

Executable World Models for ARC-AGI-3 in the Era of Coding Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Rodionov, Sergey
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Neural Cellular Automata for ARC-AGI
por: Xu, Kevin, et al.
Publicado: (2025)

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

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

Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3
por: Han, Liew Keong
Publicado: (2026)

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

Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning
por: Ouellette, Simon
Publicado: (2025)

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

ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
por: Chollet, Francois, et al.
Publicado: (2025)

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

Towards Efficient Neurally-Guided Program Induction for ARC-AGI
por: Ouellette, Simon
Publicado: (2024)

System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI
por: Kim, Sejin, et al.
Publicado: (2024)

Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute
por: Roye-Azar, Antonio, et al.
Publicado: (2025)

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
por: Pourcel, Julien, et al.
Publicado: (2025)

How Modality Shapes Perception and Reasoning: A Study of Error Propagation in ARC-AGI
por: Wen, Bo, et al.
Publicado: (2025)

The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
por: Vahdati, Sahar, et al.
Publicado: (2026)

AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
por: Zhang, Zhixing, et al.
Publicado: (2026)

SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents
por: Zhang, Zhirui, et al.
Publicado: (2026)

NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents
por: Song, Yang, et al.
Publicado: (2026)

CausalARC: Abstract Reasoning with Causal World Models
por: Maasch, Jacqueline, et al.
Publicado: (2025)

Levels of AGI for Operationalizing Progress on the Path to AGI
por: Morris, Meredith Ringel, et al.
Publicado: (2023)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
por: Guo, Chengquan, et al.
Publicado: (2024)

Pathways to AGI
por: Fletcher, Gordon, et al.
Publicado: (2026)

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
por: Wei, Anjiang, et al.
Publicado: (2025)

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects
por: Wang, Puyi, et al.
Publicado: (2026)

Executable Code Actions Elicit Better LLM Agents
por: Wang, Xingyao, et al.
Publicado: (2024)

Distributional AGI Safety
por: Tomašev, Nenad, et al.
Publicado: (2025)

Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
por: Alaswad, Feisal, et al.
Publicado: (2026)

Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving
por: Mai, Xinji, et al.
Publicado: (2025)

Coding Agent Is Good As World Simulator
por: Wang, Hongyu, et al.
Publicado: (2026)

ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents
por: Yao, Yilun, et al.
Publicado: (2026)

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
por: Ganapavarapu, Giridhar, et al.
Publicado: (2026)

Self-Programmed Execution for Language-Model Agents
por: O'Connor, Luke J.
Publicado: (2026)

From the Pursuit of Universal AGI Architecture to Systematic Approach to Heterogenous AGI: Addressing Alignment, Energy, & AGI Grand Challenges
por: Kurshan, Eren
Publicado: (2023)

PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks
por: Orimo, Yuki, et al.
Publicado: (2025)

ARC Prize 2025: Technical Report
por: Chollet, François, et al.
Publicado: (2026)

ARC Prize 2024: Technical Report
por: Chollet, Francois, et al.
Publicado: (2024)

Towards AGI A Pragmatic Approach Towards Self Evolving Agent
por: Kar, Indrajit, et al.
Publicado: (2026)

A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI
por: Sukhobokov, Artem, et al.
Publicado: (2024)

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