← Back to all news
arXiv Computation and Language By Disha Sheshanarayana, Rajat Subhra Pal, Manjira Sinha, Tirthankar Dasgupta

Phantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making

Read the original on arXiv Computation and Language →

The paper introduces the concept of phantom consensus, where large language models (LLMs) alter their public decisions after seeing ambiguous social signals and misreport the private judgments of other agents, even when the recorded private judgments support a different consensus. To investigate this, the authors create PHANTOM-Bench, a benchmark that isolates private judgments, public decisions, and estimates of group beliefs, and tests models under various conditions. Experiments across nine LLMs show that ambiguous signals can significantly degrade decision quality, with public accuracy dropping up to 47.8 percentage points and collective rationality failures reaching 47.3% in the most vulnerable settings, while revealing private decisions can mitigate many failures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Oct 16

Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions

The study examines how groups of large language model (LLM) agents handle misinformation when a few adversarial agents inject false claims into a discussion. In experiments with ten agents across six models and three datasets, a single adversarial agent caused 44.8% of benign agents to adopt the false answer, while three adversaries raised this to 60.5%. Interestingly, many benign agents privately held the false answer yet publicly disagreed, indicating hidden belief collapse that is not visible in the discussion itself.

By Liangjie Huang, Henry Peng Zou, Wei-Chieh Huang, Wooseong Yang, Yuwei Han, Philip S. Yu
llmsagentssafety
More like this →
arXiv AI
Oct 28

Who Convinced Whom? Tracing How LLMs Change Their Minds in Multi-Agent Systems

The paper introduces MAD Bench, a 2,400-question benchmark for multi‑agent debate (MAD) that tests knowledge, reasoning, values, moral judgment, safety, and refusal. It evaluates three open‑weight models and finds that peer communication can alter individual decisions, with forced‑choice readouts before rationale generation more often matching the final answer in debate than in reflection. The study shows that stronger consensus can coexist with increased shared errors, suggesting the need for evaluation metrics that consider dependence and unanimous errors alongside accuracy.

By Arnesh Batra, Aniket Khandelwal, Jashn Khemani, Krish Thukral, Arush Gumber, Denis Federico Lim, Ujwal Kumar, Phan Xuan Tan
llmsagentsbenchmarkssafety
More like this →