Transforming Integer Grids to Spatial Intuition: Perception, Not Planning, Governs ARC-AGI-3
Organizations: Independent Researcher
Abstract
Sample-efficient fluid intelligence requires agents that rapidly form working models of unfamiliar interactive environments. ARC-AGI-3 tests this across uninstructed visual games scored by Relative Human Action Efficiency, which penalizes exploratory waste quadratically. When frontier models read raw integer grids, serialization destroys spatial topology, and they spend hundreds of actions rediscovering basic boundaries and symmetries. We introduce SARBLOH, an open-weight agent built on the premise that spatial perception, not planning capacity, governs interactive reasoning on ARC-AGI-3. A zero-parameter O(HW) perception engine turns each frame, in 35 ms, into an object inventory with bipartite temporal tracking, a geometric briefing that separates proven invariants from affordance hypotheses, and an annotated canvas. Paired with a code-as-action runtime, the agent writes algorithmic hypotheses instead of low-level moves. Across eight presentations, grounded perception raises the rubric score from 3/28 to 25/28 points while cutting token use by 89.4%. On 23 held-out games, geometric invariants generalize with 100% accuracy, while single-frame affordance guesses fall to 6-50%, so active verification probes remain necessary. On the public set, Run A (briefing off) solved 143 of 183 levels in 8.2 hours at 59.4% single-pass efficiency; Run B (briefing on) reached 63.5%. Within the nine-hour budget on one Kaggle RTX PRO 6000 GPU, SARBLOH scored 16.53 on the hidden Kaggle evaluation, 13.7x the first Milestone winner.
Figures & tables
| Hidden Kaggle set (offline, 1 GPU, 9 h) | Public set (frontier APIs, unbounded) | |||||||
|---|---|---|---|---|---|---|---|---|
| Sarbloh this work | Duck first Milestone winner | Reki second Milestone winner | Prime Agent open harness | Arcgentica Symbolica | AVO NVIDIA | Provider Adapters GPT-5.5 | Provider Adapters Gemini 3.8 Flash | |
| Wall-clock limit | 9 h | 9 h | 9 h | unbounded | unbounded | unbounded | unbounded | unbounded |
| Network access | none | none | none | yes | yes | yes | yes | yes |
| Protocol | peak / single pass | – | – | self-reported | self-reported | self-reported | self-reported | self-reported |
| Open weights | ✓ | ✓ | ✓ | – | – | – | – | – |
| Backbone | Qwen3.8-Flash-Next | Qwen 3.6 27B | Gemma-4-31B | Claude Opus 5 | Claude Opus 4.6 | Opus 5 / GPT-5.6 | GPT-5.5 | Gemini 3.8 Flash |
| Role | Evidence (scored) | One-action test |
|---|---|---|
| You | Compact, multi-coloured, unique, on the lattice | Press one arrow: it moves one tile |
| Goal | Hollow box; shape repeated in the HUD | Bring the matching thing into it |
| Moves left | Long bar at the screen edge | Any action: it shrinks one unit |
| Lives | Identical copies in the HUD | Watch it on a failure or reset |
| Inventory | HUD icon matching a world object | Watch it after the modifier |
| Modifier | Small symbol, lopsided colours | Step on it: the inventory changes |
| Presentation | ls20 | r11l | Total | Int. | Tokens |
|---|---|---|---|---|---|
| /14 | /14 | /28 | 1–5 | ||
| Legacy Encoder (baseline) | 2 | 1 | 3 | 1 | 3500 |
| X1 Exploded Inventory | 2 | 1 | 3 | 2 | 180 |
| X2 Surprise Map | 3 | 1 | 4 | 2 | 270 |
| X3 Visual Routines | 7 | 8 | 15 | 4 | 240 |
| X4 Look-alike Threads | 4 | 2 | 6 | 3 | 140 |
| Check on 23 Held-Out Official Games | Empirical Generalization |
|---|---|
| Screenshot to grid, exact cells | 23/23 games (100%) |
| Agent identity (X7), keyboard games | 6/14 games (43%) |
| Moves-left gauge found (X7) | 10/20 games (50%) |
| Click handles that respond (X7) | 7/29 handles (24%) |
| Keyboard foresight fully right (X5) | 1/16 games (6%) |
Appendix figures & tables11 assets
Supplementary material from the paper’s appendix.
Appendix
| Symbol | Meaning |
|---|---|
| Environment and score (Section 2 ) | |
| grid observed at step , in | |
| grid height and width | |
| action set, Equation ( 1 ) | |
| ; ; | levels in a game; level index; levels cleared |
| ; | human baseline actions; agent actions on level |
| Parameter | Value |
|---|---|
| Games / GPU slots | 25 / 10 |
| Scheduler quantum | 20 model calls |
| Action cap per game | 2,000 actions |
| Actions per play() path | at most 100 |
| Reply cap per request / requests per turn | 12k tokens / 12 |
| Thinking without a move before the turn yields | 16,384 tokens |
| Run A: 25 games, one GPU, 8.2 h | Value |
|---|---|
| Prompt tokens served from the prefix cache | 98.4% of 1.78 B |
| Decode speed per request | 76 tok/s |
| Busy time: decode / prefill | 50.1% / 1.3% |
| Model calls / server failures | 21,224 / 0 |
| 25 public games, one GPU | Run A | Run B |
|---|---|---|
| Logged (2026) | 23 Oct | 27 Oct |
| Configuration | ||
| Briefing and map | off | on |
| Extra guardrails, stuck review | – | ✓ |
| Context drain target | 55k | 70k |
| Wall clock | 8.2 h | 5.4 h |
Visual Reasoning
Visual reasoning studies how AI systems interpret and combine visual evidence to solve spatial, relational, compositional, and physical problems.
See all 169 papers