Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?
This paper attributes the performance of an ARC-AGI-3 agent by testing four nested Codex-based agents. Results show stronger models and reasoning effort consistently improve performance, but the benefits of executable world models, simplification, and verification vary. The complete verification variant ranks first across settings but uses more resources.
-->
[Submitted on 16 Jul 2026]
Title:Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?
View a PDF of the paper titled Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?, by Sergey Rodionov
View PDF
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. We address this attribution question with four nested Codex-based agents: a textual baseline; a flexible-interface executable world model without replay verification; the same executable model with scheduled simplification; and a fixed-interface verification treatment that retains simplification and requires exact reproduction of recorded observations. The main study evaluates all four agents with gpt-5.4 and gpt-5.5 at high and xhigh reasoning effort on the public ARC-AGI-3 games. Exploratory follow-ups evaluate the textual and verification variants with gpt-5.6-sol at xhigh and max. The most robust result is that every agent variant improves with a stronger model and with greater reasoning effort. Within each model-effort setting, differences among variants are smaller than anticipated, while the effects of individual components vary across settings. Requiring a persistent executable deliverable is not universally beneficial: the textual variant outperforms the flexible-interface executable variant in both gpt-5.5 settings. Simplification improves performance in three of the four model-effort settings, with the weakest setting as the only exception. The complete verification treatment ranks first in all four settings, although it uses substantially more resources. In the gpt-5.6-sol follow-up, the verification variant fully solves every public game at both reasoning efforts, achieves about 99% RHAE, and uses fewer than half the total actions of the human baseline. Because the model postdates these games and held-out performance remains untested, this result should be interpreted as saturation of the public set only.
Comments: 31 pages, 2 figures
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.15439 [cs.AI]
(or arXiv:2607.15439v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.15439
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Sergey Rodionov [view email] [v1] Thu, 16 Jul 2026 20:18:59 UTC (1,160 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?, by Sergey Rodionov
View PDF
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-07
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)