SOURCE-LINKED INTELLIGENCE

Language-model groups overstate consensus when replaying human deliberation on a reasoning task

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We replayed 100 held-out human Wason groups with matched large language model (LLM) agent groups, seeding one belief-anchored agent per participant's pre-discussion answer and scoring agents and people with the same code. Across human scoring definitions, estimates ranged from 24.0% to 57.0%; about one fifth of participants never posted, whereas agents almost always did. Agent groups remained more consensual in two post-unblinding sensitivity analy

Read original source ↗ Open in workspace

recordType

paper

region

Global