Metraipolis › archive › dc_bf5a82f67f13
Phantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making — arXiv:2611.08971
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08971
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:33:31.797Z
- SHA-256 of the archived text
7a3d5ef44d79647194f110fd5a18bc7053db0eb97a70fc86962b461f52608d86- Stable URL of this page
https://metraipolis.com/documento/dc_bf5a82f67f13
How to cite
Phantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making — arXiv:2611.08971 — arXiv (en), https://arxiv.org/abs/2611.08971 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf5a82f67f13 (Metraipolis archive dc_bf5a82f67f13, sha256 7a3d5ef44d79647194f110fd5a18bc7053db0eb97a70fc86962b461f52608d86)
BibTeX
@misc{dcbf5a82f67f13,
title = {Phantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making — arXiv:2611.08971},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08971},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf5a82f67f13; sha256 7a3d5ef44d79647194f110fd5a18bc7053db0eb97a70fc86962b461f52608d86},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08971. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent LLM systems increasingly aggregate judgments across model instances, but reasoning about other agents can itself introduce failure. We study a setting in which LLMs shift their public decisions after observing ambiguous social signals while reporting inaccurate estimates of what other agents privately judged, even when the group's recorded private judgments do not support the apparent consensus. We call this failure phantom consensus and study it as a pluralistic-ignorance-style pattern in controlled LLM collectives. To measure this phenomenon, we introduce PHANTOM-Bench, a benchmark that separates isolated private judgments, public decisions after ambiguous social signals, elicited estimates of the group's private judgment, transparency-based recovery, and controls for neutral public text and explicit vote-following. Across nine closed- and open-weight models, ambiguous public signals consistently degrade decision quality and can turn correct private group judgments into incorrect public collective outcomes. Public accuracy drops by as much as 47.8 percentage points, and collective rationality failures reach 47.3% in the most susceptible setting. We observe substantial errors in reported group-private beliefs alongside public-stage failures, while control conditions reveal model-dependent differences in susceptibility to ambiguous and explicit peer signals. Revealing the agents' recorded private decisions repairs many failures without revealing the gold label, although recovery varies across models. Our results show that evaluating multi-agent LLM systems requires measuring not only final agreement, but whether that agreement reflects independently measured private judgments or an apparent consensus. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.08971 — 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 2026-11-09T22:30:32.049Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).