arXiv AI June 9, 2026 By Sergey Rodionov

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

arXiv:2605. 05138v2 Announce Type: replace Abstract: We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 20

Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?

arXiv:2607. 15439v1 Announce Type: new Abstract: Our previous ARC-AGI-3 agent bundled executable world modeling, scheduled simplification, and exact replay verification, leaving unclear which idea accounted for its performance.

By Sergey Rodionov

llms agents

arXiv AI

Jul 7

Auto: The AGI Compiler

arXiv:2607. 04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded.

By Jaber Jaber, Osama Jaber

llms agents benchmarks

arXiv AI

Jul 1

Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens

arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.

By Peizhi Niu, Wenjie Qu, Shangding Gu, Tianneng Shi, Yuankai Li, Ahmad Tawaha, Hend Alzahrani, Vincent Siu, Boyi Li, Chenguang Wang, Jiaheng Zhang, Basel Alomair, Ming Jin, Muhao Chen, Chi Wang, Costas Spanos, Dawn Song

llms agents benchmarks safety

arXiv Machine Learning

Jun 25

The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems

arXiv:2606. 26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems.

By Seth Dobrin, {\L}ukasz Chmiel

agents reinforcement-learning safety

arXiv AI

Jul 15

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.

By Junjie Yin, Xinyu Feng

llms agents benchmarks

arXiv AI

Jun 17

PreAct: Computer-Using Agents that Get Faster on Repeated Tasks

arXiv:2606. 17929v1 Announce Type: new Abstract: Computer-using agents drive real software through the screen -- clicking and typing -- but they solve every task from scratch: asked to repeat a task, an agent re-reads the screen, re-reasons every tap, and pays the full cost again.

By Bojie Li

llms rag agents benchmarks safety

Related stories

Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?

Auto: The AGI Compiler

Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens

The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

PreAct: Computer-Using Agents that Get Faster on Repeated Tasks