Metraipolis › archive › dc_27d3173752cc
LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems — arXiv:2609.33495
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33495
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:54:12.510Z
- SHA-256 of the archived text
d2a64499444e98e342b54cfe7089597f0527a29b55363eaaa8dc05a74d724c90- Stable URL of this page
https://metraipolis.com/documento/dc_27d3173752cc
How to cite
LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems — arXiv:2609.33495 — arXiv (en), https://arxiv.org/abs/2609.33495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27d3173752cc (Metraipolis archive dc_27d3173752cc, sha256 d2a64499444e98e342b54cfe7089597f0527a29b55363eaaa8dc05a74d724c90)
BibTeX
@misc{dc27d3173752cc,
title = {LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems — arXiv:2609.33495},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33495},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27d3173752cc; sha256 d2a64499444e98e342b54cfe7089597f0527a29b55363eaaa8dc05a74d724c90},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly deployed in multi-agent settings, where agents observe and influence one another, making social influence a key dimension of AI behavior and safety. We investigate whether LLMs' responses depend on the social identity of other agents, beyond the effect of their consensus. We construct judgment tasks with a single correct answer, and place models in a multi-agent setting where they receive incorrect answers from other agents whose social identities (AI or human, model family, or an arbitrary minimal group) are either shared with or distinct from their own. Across 12 open-weights models and nine tasks, we find a bidirectional effect of group identity on conformity to incorrect answers: in-group consensus increases conformity (in-group favoritism), whereas out-group consensus decreases it (out-group divergence). Unlike humans, for whom one ally breaking the consensus sharply reduces conformity, models are unmoved by an ally from the majority's group. Worse, a correct ally from the opposing group intensifies this bidirectional effect. Chain-of-Thought reasoning suppresses most of these effects, yet an in-group ally still reduces conformity to an incorrect out-group majority. Labeling peers as safety-aligned shifts overall conformity but leaves in-group favoritism and out-group divergence intact. These results show that group identity shapes how LLMs aggregate information across agents, independently of its correctness, and identify a manipulation surface for multi-agent AI systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.MA). Categorie arXiv: Computation and Language (cs.CL) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.33495 — 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 2026-10-07T20:24:41.703Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).