GoKawiilWe introduce Schema , a harness that has frontier models play like physicists: write each game’s mechanism as an executable program, test it against reality, and plan inside it. The name is inspired by Immanuel Kant: a schema is a rule of construction that bridges from abstract concept to concrete perception.
ARC-AGI-3: games that don’t tell you the rules ARC‑AGI‑3 gives an agent a game environment, without an explanation of what it is seeing. At each step, the agent receives a 64×64 grid of 16 color indices and a set of legal actions. The environment supplies no object list, rule sheet, stated goal, or shaped reward. There is only one way to make progress: the physicist’s way. The agent must act while its model of the game is still provisional, forming hypotheses about what the grid represents, how actions change it, and what counts as success, then revising both its model and its plan as new observations arrive. ARC‑AGI‑3 has proved exceptionally difficult for frontier models. Its official metric, Relative Human Action Efficiency (RHAE), compares an agent’s per-level action count with a first-exposure human baseline and aggregates the result across environments; 100% means completing every level of every environment at or above human-baseline action efficiency. On the Semi‑private set, verified frontier-model performance rose from 0.51% at launch in March to 7.78% with GPT‑5.6 Sol at max reasoning in July. Sol also scored 13.33% on Public set, but still far from the human reference.
0 20 40 60 80 100 Human 100% 25 Mar 15 Apr 01 May 15 May 01 Jun 15 Jun 01 Jul 15 Jul RELEASE DATE RHAE (%) Agentica TELL DreamTeam OpenClaw baseline1 Continual Harness Sol Max Terra Max Luna Opus 4.6 Max Opus 4.7 High GPT-5.5 High Opus 4.8 High Sol Max [ schema ] Opus 4.8 & Fable 5 98.98 [ schema ] GPT‑5.6 95.35 VERIFICATION Verified Self-reported EVALUATION SET Public Semi-private Figure 1. ARC‑AGI‑3 RHAE results reported through July 2026. Filled markers denote ARC Prize-verified evaluations; hollow markers denote self-reported evaluations on the Public set. Magenta identifies Schema. Both Schema results are self-reported and have not been verified by ARC Prize.
Schema, the harness we introduce today, reaches 99% on the ARC‑AGI‑3 Public set using Claude Opus 4.8 and Fable 5, and 95.35% using GPT‑5.6 Sol. It does not change the underlying model weights. Instead, it changes the process around them: how observations are turned into a working model of the game, how predictions are tested against the interaction history, and how plans are executed and revised. Both scores come from a fixed fallback rule: Opus 4.8 and Sol xhigh run first; games scoring below 80 are rerun with Fable 5 and Sol max, respectively, and the higher per-game score is retained. The takeaway: how you use the model matters a lot. The rest of this post shows the arrangement.
Thinking like a physicist Schema thinks like a physicist. Before a physicist can write down a law, they must decide what the law is about. Which parts of an observation are objects? Which properties define the state? Only then can they ask how that state changes. Schema formalizes these questions as two problems. State grounding turns raw observations into objects, variables, and relations that can be tracked. Mechanism discovery finds how that state changes under an action and writes the rule as an executable program. Our earlier system, VIGA, focused on the first problem. Through analysis-by-synthesis against a graphics engine, it recovered scene programs from continuous visual input far richer than an ARC grid. Other systems like WorldCoder focus on the second: they learn transition programs from trajectories but begin with an already structured state representation. We believe these two problems must be solved jointly, with the agent constructing the state representation and the transition rules.
LEVEL 2 · MECHANISM DISCOVERY WorldCoder (state, action, state′) → transition program step() How the world moves between moments — the rule, written as a program. Each game hides mechanisms like these: spring wall refuel ring color rotator derive the rule on the grounded state a counterexample can indict the representation itself LEVEL 1 · STATE GROUNDING VIGA observation → state program What the world is — objects, quantities, names, invented from raw pixels. Nothing says which pixels count as the player, a wall, a counter. player? counter? [ schema ] solves both levels, jointly — in one editable program. Figure 2. The two levels of abstraction. Level 1 invents the state — which pixels form the player, a wall, a counter. Level 2 recovers the mechanism over that state, like the spring walls, refuel rings, and color rotators above. Schema holds both in one editable program: when a rule refuses to stay consistent with experiments, the counterexample can indict the representation itself.
State grounding and mechanism discovery cannot be resolved independently. A state representation that appears plausible at first may prove inadequate when no consistent transition rule can explain the outcomes of subsequent experiments. In Schema, the state representation and transition rules are jointly encoded in the same editable program. When an observation contradicts a prediction, the agent can revise either the representation or the rule, then update the other to restore a consistent model. This mirrors how physicists work: when predictions fail persistently, they do not only adjust the law. They change what the state is. The cleanest case is the birth of special relativity. When Michelson and Morley could not detect the medium light was supposed to wave in, Lorentz took the first route: keep the aether, patch the rules with contraction hypotheses that absorbed the null result. Einstein took the second: in special relativity, he discarded the aether as part of the state and made simultaneity frame-relative, yielding a simple electrodynamics of moving bodies. ARC‑AGI‑3 requires the agent to construct both layers from raw observations. The grid identifies neither objects nor goals, so the agent must decide which patterns correspond to entities such as the player, walls, and counters, infer how actions transform them, and determine which configurations count as progress or completion. Even the goal predicate—implemented in Schema as is_goal —must be inferred from interaction. Core idea. The latent world representation is a program, not a vector — so it is interpretable (a text file you can read and diff), verifiable (replayable against recorded reality, belief by belief), and searchable (a program is a simulator; planning inside it is free).
next turn — the cycle repeats surprise → plan voided, back to deliberation observe The raw grid — pixels. Every object in it was invented by the agent. deliberate An open-ended reasoning episode that ends only in a committed queue of actions. execute Runs the queue with a per-step self-check against the world model’s predictions. record Appends every real transition to the Timeline. append-only TIMELINE — GROUND TRUTH deliberate INSIDE ONE DELIBERATION — THE INNER LOOP mismatch — fix the bug green theorize write_code Edit the theory of the game as step(state, action). certify run_backtest Replay every recorded transition — exact match, or a pointed bug. plan run_bfs Search inside the certified program — zero real cost. commit commit_actions The only channel from thinking to action. PERSISTENT MEMORY — THE AGENT’S “WEIGHTS” world_model.py notes.md Timeline append-only RUNNING EXAMPLE — LS20 · REAL TRACE Opus 4.8 · 642 actions vs human 780 · RHAE 100 [observe] 64×64 grid, 16 colors, actions 0–4 — a plus-shaped sprite, a cyan+maroon block, a framed maroon glyph, a color-11 bar. [deliberate] notes.md: the avatar is the 5×5 cyan+maroon block — the plus sprite is static; the bar is a move budget that depletes only on successful moves. [deliberate] write step() · run_backtest → world_model_v5.py replays 36/36 recorded transitions exactly. [execute] commit [2,2,2,3,2,2] → surprise: 77 cells mispredicted — the block repainted the indicator maroon. plan voided. [record] repaint rule encoded · backtest green · run_bfs finds the shortest plan → level up. 7 levels this way: 642 actions vs the 780-action human baseline. The outer loop. The agent runs a four-stage cycle against the game: observe → deliberate → execute → record. Record is the system’s immutable interaction history. The agent can revise its hypotheses and working notes, but it cannot alter the observations it received or the actions it took. During each deliberation, the agent updates its theory of the game as a step(state, action) program. It tests the program against the complete interaction history with run_backtest , uses any mismatch to locate errors, searches the resulting model for a plan with run_bfs , and records its working conclusions in notes.md . None of these operations changes the environment. Only commit_actions sends actions to the game, separating internal modeling and search from external interaction. Action for discovery. The agent does not act only to reach the goal; it also acts to investigate the hidden mechanisms. When multiple candidate rules remain consistent with the recorded history, the agent searches for an experiment that separates them: an action for which they predict different outcomes. It commits that action, compares the observation with the competing predictions, updates step() , and reruns the backtest. This targeted experimentation is also efficient under the official metric, which applies a squared penalty to excess actions (details below): the best experiment is the one that resolves the most uncertainty with the fewest real interactions. Reality outranks the model. During execution, every real transition is checked against the theory’s prediction. A single mismatch stops execution of the current plan. The agent returns to deliberation with the mismatched transition as a counterexample and must revise the model to account for it before planning resumes. Planning moves into the model. Once step() reproduces every transition in the recorded history, the agent can search for a solution inside the model without spending additional environment actions. Only the resulting plan is executed in the game. Across levels, this is how an accurate model translates into the action efficiency reflected in the 98.98% score. Figure 3. The Schema control loop, steppable — scroll to walk it: the four-stage outer cycle and its append-only Timeline, a zoom into one deliberation (theorize → certify → plan → commit), then a real LS20 trace playing out at each stage.
What the numbers say The metric, in full. The official ARC‑AGI‑3 evaluates performance in Relative Human Action Efficiency (RHAE), which compares the number of actions used by the agent with an upper-median first-time human baseline for each completed level. The per-level score is (human actions ÷ agent actions)² , capped at 1.15 . Within each game, levels receive increasing weights from 1 to n, so later levels contribute more to the game score. A completion cap based on the same weights prevents a game from receiving 100% unless every level is cleared. The benchmark score is the average of the game scores. All environment actions, including exploratory ones, count toward the agent’s total; because the efficiency ratio is squared, additional actions reduce the score sharply. Thus, 98.98% is an aggregate measure of completion and action efficiency—not the percentage of games solved.
0 1 2 3 4 5 6 7 0× 0.5× 1× 1.5× 2× CUMULATIVE ACTIONS TAKEN (× HUMAN BASELINE) LEVELS COMPLETED Human baseline · 776 actions Agent A · 785 actions · RHAE 97.7% Agent B · 1591 actions · stalls at 6/7 COMPLETION ≠ EFFICIENCY A clears 7/7 near the human budget; B spends 2.7× and stalls, so 97.7% vs <14% Figure 4. RHAE rewards both completion and action efficiency. Agent A completes all seven levels in 785 actions, close to the 776 actions used by the human baseline. Agent B uses 1,591 actions across the first six levels—2.7 times the corresponding human baseline—and fails to complete Level 7. Because RHAE squares the action-efficiency ratio and caps the score according to completion, Agent B scores below 14%.
... continue reading