AwesomeREA.org

2026 · Preprint

Schema: Discovering Unknown Environments via Agentic Program Induction

Guanning Zeng; Jiani Wang; Wenjie Ma; Shaofeng Yin; Chenyang Wang; Shichen Liu; Angjoo Kanazawa; Wode Ni; Xiuyu Li; Andrea Zanette; Haiwen Feng

Infers executable models of game state and transition rules from interaction. Agents revise these models against recorded history, search within them, and compare predicted observations with real outcomes while executing plans.

Scope and limitations

Evaluation uses 25 public ARC-AGI-3 games, 21 public DiG-bench games and MazeBench. Matching recorded transitions establishes history consistency, not original-source recovery or correctness on unseen states. RHAE measures completion and environment-action efficiency, not elapsed time or total computation. Component ablations cover ten ARC games; MazeBench compares recorded trajectories with a leaderboard median rather than a controlled human experiment. Transfer to arbitrary software or stochastic environments is not demonstrated.

Why it fits this collection

Provides a concrete observation-to-program-and-replay loop for black-box behavioral reconstruction, while distinguishing a useful predictive model from a complete game clone.

Publication and review details

Venue
arXiv
Status
Preprint
Publication / posting date
September 30, 2026
Date source
arXiv v1 first-submission date; the July project announcement and October repository revision are separate.
First arXiv submission
September 30, 2026
arXiv
2609.39140
Reviewed arXiv version
v1
DOI
10.48550/arxiv.2609.39140

The eleven-author v1 list and title match arXiv and the current project. DataCite registered the arXiv DOI on 2026-10-01; the article uses arXiv’s non-exclusive distribution license. The author-linked MIT code was inspected at 84c075fadfe937b97a3d1ad2acb42d1233f55ffe. Benchmark engines/services retain separate requirements. The linked trace dataset README at 0a0858a9e61a68d1e83142d9e4e3d66fc779c403 describes 50 July ARC trajectories, including a mixed-model collection; it is not verified as the complete September-paper release. No trace-data license was verified. No trace archives, models or benchmark engines were downloaded or executed.

Sources reviewed

Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.

Primary sources

  1. https://arxiv.org/abs/2609.39140
  2. https://arxiv.org/html/2609.39140v1
  3. https://api.datacite.org/dois/10.48550/arxiv.2609.39140
  4. https://schema-harness.github.io/
  5. https://guanning03.github.io/schema-webpage/
  6. README.md GitHub · guanning03/Schema · Revision 84c075f
  7. LICENSE GitHub · guanning03/Schema · Revision 84c075f
  8. https://huggingface.co/datasets/schema-harness/arc-agi-3-schema-traces/blob/0a0858a9e61a68d1e83142d9e4e3d66fc779c403/README.md