Metraipolis › archive › dc_3c0b5ccf61fe

AVCORP: Identifying and Resisting Deception via Communication Theory and Theory of Mind — arXiv:2611.10176

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10176
License (as archived)
CC0-1.0
Archived
2026-11-10T18:40:47.346Z
SHA-256 of the archived text
7c542c9dbe318c34ea88a57c7b53590653f543fda6c8e96f67f6bbd2dbc946c8
Stable URL of this page
https://metraipolis.com/documento/dc_3c0b5ccf61fe

How to cite

AVCORP: Identifying and Resisting Deception via Communication Theory and Theory of Mind — arXiv:2611.10176 — arXiv (en), https://arxiv.org/abs/2611.10176 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3c0b5ccf61fe (Metraipolis archive dc_3c0b5ccf61fe, sha256 7c542c9dbe318c34ea88a57c7b53590653f543fda6c8e96f67f6bbd2dbc946c8)
BibTeX
@misc{dc3c0b5ccf61fe,
  title = {AVCORP: Identifying and Resisting Deception via Communication Theory and Theory of Mind — arXiv:2611.10176},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10176},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3c0b5ccf61fe; sha256 7c542c9dbe318c34ea88a57c7b53590653f543fda6c8e96f67f6bbd2dbc946c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10176. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Today's LLM-based agents are vulnerable to deception by users and other agents. Defending against deception requires Theory of Mind (ToM) reasoning to infer the beliefs and goals of others as well as modeling tactics based on communication theory. To enable training models to detect deception, we adopt the well-known deception game, Avalon. We present a corpus, AVCORP, of 5,000 annotated utterances from 250 games of Avalon. AVCORP includes (1) 37 tactics mapped to a 4x4 behavior matrix, and (2) reasoning traces capturing abductive hypotheses, suspicion levels, and nested ToM beliefs. We train Qwen3-8B on AVCORP and evaluate it on 25 held-out games and 20 games played by humans. On held-out games, our best trained detector outperforms its untrained baseline and frontier models (GPT-5.6 Sol, Gemini 3.1 Pro, DeepSeek-V4-Pro), matching Claude Opus 5.5. On human games, every trained detector exceeds the untrained model in F1 score across all rounds.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.10176 — 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 2026-11-10T18:37:37.480Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).