发表机构
LMU Munich; Royal Holloway, University of London（慕尼黑大学; 伦敦大学皇家霍洛威学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过正式模型和陪审团定理，分析审议中智能体选择性披露证据对集体准确性的影响，发现群体智慧在特定条件下出现，且受证据获取机制和初始多样性影响。
AI 中文摘要
我们分析了一个正式的审议模型，其中智能体以概率方式获取证据，并选择性地向同伴披露这些证据以诱导意见改变。我们提出了理论和模拟结果，以解决这个问题：审议是否提高群体的集体准确性？通过一个陪审团定理，我们描绘了允许群体智慧在几步审议后出现的条件，并通过模拟表明，这种效应如何对证据获取机制敏感，并隐含地对初始证据分布中的多样性敏感。
英文摘要
We analyze a formal model of deliberation in which agents have probabilistic access to evidence and selectively disclose it to their peers in order to induce opinion change. We present theoretical and simulation results that tackle the question: does deliberation improve the collective accuracy of the group? Through a jury theorem we chart the conditions that allow wisdom of crowds to emerge after a few steps of deliberation, and, through simulations, we show how this effect is sensitive to the evidence acquisition mechanism and, implicitly, to the diversity in the initial evidence distribution.
CommentsFull version with proofs of ADT 2026 paper
