Metraipolis › archive › dc_ef6cc37e0fa4

Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version) — arXiv:2608.11229

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11229
License (as archived)
CC0-1.0
Archived
2026-10-19T05:15:11.267Z
SHA-256 of the archived text
ccba9cd046ed4d21e9a6880f29d1420e8566175d7ace32063b02e80fa057f18f
Stable URL of this page
https://metraipolis.com/documento/dc_ef6cc37e0fa4

How to cite

Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version) — arXiv:2608.11229 — arXiv (en), https://arxiv.org/abs/2608.11229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef6cc37e0fa4 (Metraipolis archive dc_ef6cc37e0fa4, sha256 ccba9cd046ed4d21e9a6880f29d1420e8566175d7ace32063b02e80fa057f18f)
BibTeX
@misc{dcef6cc37e0fa4,
  title = {Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version) — arXiv:2608.11229},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11229},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef6cc37e0fa4; sha256 ccba9cd046ed4d21e9a6880f29d1420e8566175d7ace32063b02e80fa057f18f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Comparative feedback, asking people which of two behaviors they prefer, has become a standard way to align robot and agent behavior with human intent when the reward itself cannot be specified directly. Preference-based reward learning typically casts the human teacher as a passive oracle answering learner-generated queries. We argue this forfeits the teacher's defining advantage: knowledge of the objective. A teacher who knows the target can construct training examples more efficiently than any learner-driven acquisition strategy, an advantage that widens as the reward's feature dimension grows. However, exploiting this advantage requires an accurate model of what the learner currently knows. We therefore recast preference learning as a human-autonomy team problem coupling two behavioral models: the teacher maintains a model of the learner to design an informative curriculum, and the learner maintains a second-order model of the teacher's model, emitting structured preference constraints (understanding statements) that keep the teacher's model of the learner synchronized. In simulation, an informed teacher outperforms learner-led selection; teacher-model drift under alternating teachers erodes this advantage; and understanding statements repair it, with second-order (ToM-2) statements outperforming mean-belief statements when the teacher's error about the learner is concentrated in a particular direction rather than spread evenly.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.11229 — 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 2026-10-19T05:08:46.603Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).