Metraipolis › archive › dc_b3e2adaa6d52

Peer Influence across Heterogeneous AI Models — arXiv:2610.03095

Source
arXiv
Original
https://arxiv.org/abs/2610.03095
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:30.456Z
SHA-256 of the archived text
ff0d36e9dace539dea5f76530bdd5de2a7728b850d2174c09a655307ca9c74bc
Stable URL of this page
https://metraipolis.com/documento/dc_b3e2adaa6d52

How to cite

Peer Influence across Heterogeneous AI Models — arXiv:2610.03095 — arXiv, https://arxiv.org/abs/2610.03095 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b3e2adaa6d52 (Metraipolis archive dc_b3e2adaa6d52, sha256 ff0d36e9dace539dea5f76530bdd5de2a7728b850d2174c09a655307ca9c74bc)
BibTeX
@misc{dcb3e2adaa6d52,
  title = {Peer Influence across Heterogeneous AI Models — arXiv:2610.03095},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03095},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b3e2adaa6d52; sha256 ff0d36e9dace539dea5f76530bdd5de2a7728b850d2174c09a655307ca9c74bc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03095. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When two AI agents disagree, who persuades whom? As multi-agent systems increasingly combine language models of different families and sizes, the answer can determine which judgments survive interaction. Measuring persuasion as the probabilistic shift in an agent's decision after a single exchange with a dissenting peer, we test seven open-weight models across three language understanding tasks. We find that persuasion is strong: when models disagree, receivers often abandon their initial judgment after seeing a peer's answer and explanation. Surprisingly, however, neither standalone certainty nor model scale reliably predicts persuasion dynamics. Models producing almost perfectly consistent decisions in isolation can be among the most susceptible to persuasion, and small models can match larger ones as persuaders and resist their influence just as effectively. Furthermore, we show that the size of the shift depends more on the susceptibility of the listener than on the persuasiveness of the speaker. Persuasion patterns are therefore specific to each model pairing, with heterogeneity amplifying persuasion in some combinations and suppressing it in others, allowing a dissenting agent running a small model to overturn the judgments of a much larger one. These findings show that the behavior of interacting models cannot be inferred from their individual properties but must be evaluated in the combinations in which they will operate.

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); Computers and Society (cs.CY); Physics and Society (physics.soc-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.03095 — 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 2026-10-05T22:45:55.674Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).