Metraipolis › archive › dc_693e602c072a

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation — arXiv:2609.24146

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24146
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:34.335Z
SHA-256 of the archived text
bd1b304e85a4cffef39ce4f37e2c9bad8f8643e18f375ea982c9912e3c1cca7f
Stable URL of this page
https://metraipolis.com/documento/dc_693e602c072a

How to cite

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation — arXiv:2609.24146 — arXiv (en), https://arxiv.org/abs/2609.24146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_693e602c072a (Metraipolis archive dc_693e602c072a, sha256 bd1b304e85a4cffef39ce4f37e2c9bad8f8643e18f375ea982c9912e3c1cca7f)
BibTeX
@misc{dc693e602c072a,
  title = {Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation — arXiv:2609.24146},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24146},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_693e602c072a; sha256 bd1b304e85a4cffef39ce4f37e2c9bad8f8643e18f375ea982c9912e3c1cca7f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language model agents are increasingly used to simulate social interaction, and the resulting transcripts read as though the agents understand one another. We ask whether that appearance rests on a model of the partner's mind or on the surface record of what the partner said. We build a social simulation in which both questions have exact answers: 40 multi-issue negotiations whose hidden preference weights and whose full Pareto frontier are known by construction. Two model families negotiate across 160 dyads, every transcript is frozen before any measurement, and 2880 counterfactual probes then hold the evidence byte identical while moving one factor at a time: the reader's own stake, the partner's tone, an identity label, and the order of recursion. The agents are socially fluent and economically poor. They reach agreement in 96.2% of dyads with 0 protocol failures, yet only 0.7% of deals land on the Pareto frontier, they leave 20.5% of the available joint value unclaimed, and they miss the one issue on which their interests are perfectly aligned in 76.6% of deals; on the frontier and on that aligned issue, a package drawn at random from the set both sides would accept does as well. The probes locate the failure. Swapping only the reader's own payoff sheet, while the partner's words and offers stay identical, moves the inferred top priority by 15.0 percentage points, which is egocentric projection rather than inference, while a tone rewrite moves it by 5.3 percentage points and an identity label by 0.0. Most tellingly, an agent predicts what its partner believes about it 72.5% of the time while that partner's belief is itself correct only 51.2% of the time: the agents track the conversation far better than they track the mind behind it.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.24146 — 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 2026-10-09T06:58:09.375Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).