# ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence

arXiv: https://arxiv.org/abs/2603.24621 · HTML: https://mlsanity.com/paper/2603.24621/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 3 of its 15 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 3 of 3)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)

## Built on by (most cited first, 30 of 37)

- [Rethinking the Evaluation of Harness Evolution for Agents](https://mlsanity.com/paper/2607.12227/) (2026)
- [PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning](https://mlsanity.com/paper/2607.20064/) (2026)
- [OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3](https://mlsanity.com/paper/2607.01531/) (2026)
- [Workspace Optimization: How to Train Your Agent](https://mlsanity.com/paper/2605.09650/) (2026)
- [Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3](https://mlsanity.com/paper/2607.28287/) (2026)
- [Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models](https://mlsanity.com/paper/2608.09696/) (2026)
- [Twin: Playing an Unknown Game with a Test-Time Digital Twin](https://mlsanity.com/paper/2608.14490/) (2026)
- [Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning](https://mlsanity.com/paper/2605.00347/) (2026)
- [Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse](https://mlsanity.com/paper/2605.09965/) (2026)
- [Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?](https://mlsanity.com/paper/2607.15439/) (2026)
- [Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning](https://mlsanity.com/paper/2608.03571/) (2026)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning](https://mlsanity.com/paper/2605.13037/) (2026)
- [Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3](https://mlsanity.com/paper/2605.25931/) (2026)
- [Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym](https://mlsanity.com/paper/2604.09338/) (2026)
- [Agentick: A Unified Benchmark for General Sequential Decision-Making Agents](https://mlsanity.com/paper/2605.06869/) (2026)
- [Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners](https://mlsanity.com/paper/2605.08019/) (2026)
- [GIM: Evaluating models via tasks that integrate multiple cognitive domains](https://mlsanity.com/paper/2605.18663/) (2026)
- [Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction](https://mlsanity.com/paper/2607.08233/) (2026)
- [EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning](https://mlsanity.com/paper/2609.35047/) (2026)
- [Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes](https://mlsanity.com/paper/2609.36777/) (2026)
- [VISTA: A Visual Harness for Reasoning in an Interactive World](https://mlsanity.com/paper/2610.02200/) (2026)
- [The Boundaries of Automation: A Theory of Persistent Human Participation](https://mlsanity.com/paper/2607.21547/) (2026)
- [Benchmark-Based Comparative Assessment of Publicly Benchmarked Indian Foundation Models: A Capability and Evaluation-Maturity Framework](https://mlsanity.com/paper/2608.11891/) (2026)
- [Framework and Benchmark for Code-Driven Agentic Testing in Web Development](https://mlsanity.com/paper/2609.00081/) (2026)
- [GameBoyWorlds: A Testbed for Self-Improvement in Embodied Video Games](https://mlsanity.com/paper/2609.32093/) (2026)
- [Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments](https://mlsanity.com/paper/2609.32208/) (2026)
- [Schema: Discovering Unknown Environments via Agentic Program Induction](https://mlsanity.com/paper/2609.39140/) (2026)
- [On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D](https://mlsanity.com/paper/2610.00820/) (2026)
- [Kepler: Auditable World Models for ARC-AGI-3](https://mlsanity.com/paper/2610.00834/) (2026)

## Abstract (arXiv)

We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents must explore, infer goals, build internal models of environment dynamics, and plan effective action sequences without explicit instructions. Like its predecessors ARC-AGI-1 and 2, ARC-AGI-3 focuses entirely on evaluating fluid adaptive efficiency on novel tasks, while avoiding language and external knowledge. ARC-AGI-3 environments only leverage Core Knowledge priors and are difficulty-calibrated via extensive testing with human test-takers. Our testing shows humans can solve 100% of the environments, in contrast to frontier AI systems which, as of March 2026, score below 1%. In this paper, we present the benchmark design, its efficiency-based scoring framework grounded in human action baselines, and the methodology used to construct, validate, and calibrate the environments.