# Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

arXiv: https://arxiv.org/abs/2607.28287 · HTML: https://mlsanity.com/paper/2607.28287/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 19 of its 66 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 19 of 19)

- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [Continual Harness: Online Adaptation for Self-Improving Foundation Agents](https://mlsanity.com/paper/2605.09998/) (2026)
- [ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence](https://mlsanity.com/paper/2603.24621/) (2026)
- [Measuring the environmental impact of delivering AI at Google Scale](https://mlsanity.com/paper/2508.15734/) (2025)
- [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026)
- [Assessing Adaptive World Models in Machines with Novel Games](https://mlsanity.com/paper/2507.12821/) (2025)
- [Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents](https://mlsanity.com/paper/2509.03581/) (2025)
- [Executable World Models for ARC-AGI-3 in the Era of Coding Agents](https://mlsanity.com/paper/2605.05138/) (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)
- [Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks](https://mlsanity.com/paper/2512.24156/) (2025)
- [The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning](https://mlsanity.com/paper/2603.13372/) (2026)
- [Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality](https://mlsanity.com/paper/2607.03691/) (2026)
- [Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents](https://mlsanity.com/paper/2602.00929/) (2026)
- [Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?](https://mlsanity.com/paper/2607.15439/) (2026)
- [NVIDIA-labs OO Agents: Native Python Object-Oriented Agents](https://mlsanity.com/paper/2607.20709/) (2026)
- [Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3](https://mlsanity.com/paper/2605.25931/) (2026)
- [Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning](https://mlsanity.com/paper/2606.16576/) (2026)

## Built on by (most cited first, 7 of 7)

- [VISTA: A Visual Harness for Reasoning in an Interactive World](https://mlsanity.com/paper/2610.02200/) (2026)
- [Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit](https://mlsanity.com/paper/2608.02302/) (2026)
- [Schema: Discovering Unknown Environments via Agentic Program Induction](https://mlsanity.com/paper/2609.39140/) (2026)
- [Kepler: Auditable World Models for ARC-AGI-3](https://mlsanity.com/paper/2610.00834/) (2026)
- [Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks](https://mlsanity.com/paper/2610.11794/) (2026)
- [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026)
- [Write Once, Plan Many: Building Reusable Visual Planning Systems from One Scene](https://mlsanity.com/paper/2610.19234/) (2026)

## Abstract (arXiv)

ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action efficiency because every move counts. We formalize these environments as parameterized rendered deterministic Moore machines and introduce Tycho, a coding-agent system that constructs and uses game-specific models during interaction. Tycho separates actionable observations from intermediate animation, level-completion, and game-over frames. From this structured history, an agent can model, test, plan with, repair, or bypass a free-form executable hypothesis. In one matched public-set run per policy, we compare four orchestration policies on all 25 public games using Claude Opus 4.8 under matched inference budgets. Actor-requested delegation to a model builder obtains the highest observed mean Relative Human Action Efficiency (RHAE), 88.49. With this selected policy, GPT-5.6 Sol and Opus 5 both reach 100.00 RHAE and complete all 183 levels. Their game-balanced first-run human-replay midranks are 98.5 and 100.0. Opus 5 uses 61% fewer scored actions than the aggregate official human baselines. Automatic repair after verification failures produces models that reproduce observed transitions much more accurately, yet reaches only 83.07 RHAE. Transition match indicates whether a simulator reproduces observed dynamics, not whether it has identified the objective or improves the next action. Strong play also requires deciding when to construct, repair, use, or bypass a model. We call this joint problem active abstraction: generating a testable model from costly interaction and deciding when acquiring or using it is worth its cost.