Metraipolis › archive › dc_697fb370d85f

Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces — arXiv:2608.11354

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.11354
License (as archived): CC0-1.0
Archived: 2026-10-19T05:15:20.124Z
SHA-256 of the archived text: d82bd51fe67a085166dc55c0b472d4fb711203361e26f22b6c03435b2f966831
Stable URL of this page: https://metraipolis.com/documento/dc_697fb370d85f

How to cite

Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces — arXiv:2608.11354 — arXiv (en), https://arxiv.org/abs/2608.11354 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_697fb370d85f (Metraipolis archive dc_697fb370d85f, sha256 d82bd51fe67a085166dc55c0b472d4fb711203361e26f22b6c03435b2f966831)

BibTeX

@misc{dc697fb370d85f,
  title = {Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces — arXiv:2608.11354},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11354},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_697fb370d85f; sha256 d82bd51fe67a085166dc55c0b472d4fb711203361e26f22b6c03435b2f966831},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11354. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern recommender systems treat observed actions as reliable proxies for user preferences, yet interactions often reflect exploration or comparison rather than stable preference expression. As interfaces evolve from static layouts toward generative UIs and immersive extended reality (XR), the need for deeper, modality-agnostic user understanding grows: these adaptive environments must decide not only what to present but where, when, how prominently, and most importantly why a user acts. We propose an Inverse Theory of Mind (IToM) pipeline that reasons backward from observed interactions to infer the beliefs, preferences, and decision-making traits that explain behavior. The pipeline reconstructs each user's decision context, including what was chosen and what alternatives were available, applies LLM-driven counterfactual reasoning to produce evidence-grounded natural-language belief statements, and synthesizes these beliefs through multi-hypothesis abductive inference into a structured user persona. We evaluate on the OPeRA dataset against ground-truth personality assessments, attitudinal surveys, and interview-based personas across four tasks: next action prediction, shopping attitude alignment, Big Five personality inference, and held-out category prediction. Results show that inferred personas match or exceed ground-truth personas and that multi-hypothesis reasoning is essential for accurate personality prediction. We further demonstrate cross-modal transferability with a persona-driven spatial banking application on VisionOS.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.11354 — 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 2026-10-19T05:08:46.621Z 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).