Metraipolis › archive › dc_9a6672ecb5bf

How Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3 — arXiv:2610.34523

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.34523
License (as archived)
CC0-1.0
Archived
2026-10-27T07:57:33.063Z
SHA-256 of the archived text
b1ca1ef66bdd36259bc5fd4c6dcc9bc8f9597cc36f784b63517efed7c6efc3bb
Stable URL of this page
https://metraipolis.com/documento/dc_9a6672ecb5bf

How to cite

How Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3 — arXiv:2610.34523 — arXiv (en), https://arxiv.org/abs/2610.34523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9a6672ecb5bf (Metraipolis archive dc_9a6672ecb5bf, sha256 b1ca1ef66bdd36259bc5fd4c6dcc9bc8f9597cc36f784b63517efed7c6efc3bb)
BibTeX
@misc{dc9a6672ecb5bf,
  title = {How Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3 — arXiv:2610.34523},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34523},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9a6672ecb5bf; sha256 b1ca1ef66bdd36259bc5fd4c6dcc9bc8f9597cc36f784b63517efed7c6efc3bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning through exploration and using newly acquired knowledge to achieve goals are central capabilities of general intelligence. Understanding these capabilities requires tracing how learners build, use, and revise world models during interaction. We construct the first dataset that records how humans discover and use the mechanisms of novel environments, using ARC-AGI-3 as a testbed: 144 trajectories from 64 participants across 25 public games, each pairing time-synchronized actions with think-aloud audio, plus 250 trajectories from large language model (LLM) agents with and without harnesses on the same games. We annotate mechanism triggers and recognition, action purposes, and errors and recovery, linking changes in understanding to the observations and actions that support them. We analyze characteristics of human cognition and compare them with those of LLM agents. Both groups anticipate mechanisms and use familiar analogies. Qualitative representations are more common in successful human trajectories than in successful LLM trajectories (50.0% versus 14.3%). Humans more often explore unfamiliar situations without a concrete hypothesis, while hypothesis testing is common in both groups. We also trace how learners recover through belief revision, replanning, and execution correction. As LLMs with well-designed harnesses reach saturated performance on public ARC-AGI-3 games, our cognitive analyses motivate next-generation benchmarks that challenge familiar priors, require accumulated evidence and abstraction, and test planning through subgoals, experimentation, and recovery. Our dataset is available at [ this https URL ]( this https URL ).

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.34523 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-27T07:55:30.690Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).