| @@ -0,0 +1,19 @@ |
| 1 | +# ARC-AGI-3 |
| 2 | + |
| 3 | +Games with no instructions. Each is a small world on a 64×64 screen in sixteen colours; you are not told the rules, only which actions you have (four directions, interact, click a point, undo, reset). Clear its levels in as few actions as a person would. This is the [ARC Prize 2026](https://arcprize.org/arc-agi/3) benchmark, on its own official toolkit and games, played offline. |
| 4 | + |
| 5 | +## Scoring |
| 6 | + |
| 7 | +ARC's own RHAE: for each level you clear, (the human baseline's actions ÷ your actions)², capped at 1.15, weighted by the level's number; a game's score is that as a percentage of all its levels. The check plays the season's five games, up to 400 actions each, and your score is the mean. Uncleared levels score 0; most agents score close to that. |
| 8 | + |
| 9 | +## Your agent |
| 10 | + |
| 11 | +Exactly an [ARC-AGI-3-Agents](https://github.com/arcprize/ARC-AGI-3-Agents) agent: `agent.py` with a class `Agent` that has `choose_action(frames, latest_frame)` (and, if you like, `is_done(frames, latest_frame)`). `latest_frame` is the toolkit's `FrameData`: the frame layers, `state`, `levels_completed`, `win_levels` and `available_actions`. Return a `GameAction`, or `(GameAction.ACTION6, {"x": .., "y": ..})` for a click. Your agent plays through the official toolkit, in its own process, against the referee's local server; it never sees a game's source. |
| 12 | + |
| 13 | +## The games, season 1 |
| 14 | + |
| 15 | +LS20, FT09, VC33, SP80 and LP85, from the public set (`referee/games.txt`, files in `referee/environment_files/`). |
| 16 | + |
| 17 | +## Credits |
| 18 | + |
| 19 | +The toolkit, the engine and the games are © 2026 ARC Prize Foundation, under the MIT licence, kept with their notices. ARC Prize and ARC-AGI are the Foundation's names; this project is not affiliated with it. The referee and the viewer, which draws frames in the official palette, are this project's, under MIT. |
shoal committed 2 weeks ago
0 parents
commit