Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote. Yet ensuring that every voter encounters a representative sample of the reason space, the coverage problem, remains an open challenge, particularly at scale and in adversarial or strategically motivated electorates. This paper introduces a way of evaluating solutions using the LLM-based Agentic Bipolar Argumentation Simulator, grounded in a framework which formalises a poll as a six-tuple <Jend, Jopp, Ratt, Renh, VA, VR> of endorsing and opposing justifications, attack and enhance relations, and shareholder- and relation-weights. ABAS simulates N autonomous shareholder agents, each assigned a latent opinion according to desired distributions in [-1, 1], who sequentially vote, choose or author justifications, and optionally submit argumentation-graph links. The simulator implements recommendations that rank existing justifications by their observable endorsement mass. It evaluates the mechanism's success by coverage, namely the fraction of the corpus reason-tag set represented in the K recommendations presented to each shareholder, as a solution to the NP-hard Subsuming Justification Problem. Reported experiments characterise how creativity rate (pown), recommendation size (K), argumentation density (plinks), and population size (N) affect coverage and corpus diversity. In an authenticated electorate where Sybil attacks are impossible and only the relation graph is gameable, we stress-test the scoring with coordinated strategic voting attacks: a tag-flood attack collapses coverage, while author-count relation weighting through a reversed-PageRank rule resists the flood markedly better than uniform weights.

翻译：审议性投票通过让股东在投票前接触广泛论证，有望改善集体决策。然而，确保每位投票者都能接触到理由空间的代表性样本（即覆盖问题）仍然是一个开放挑战，尤其是在大规模、对抗性或策略性动机的选民群体中。本文基于一个将投票形式化为六元组 <赞同理由集、反对理由集、攻击关系、增强关系、股东权重、关系权重> 的框架，引入了一种利用基于大语言模型的代理双极论证模拟器评估解决方案的方法。该模拟器模拟 N 个自主股东代理，每个代理根据所需的 [-1, 1] 分布分配潜在意见，这些代理依次投票、选择或创作理由，并可选地提交论证图链接。模拟器通过推荐机制，依据可观察的赞同质量对现有理由进行排序，并通过覆盖率（即每个股东收到的 K 条推荐中代表语料库理由标签集的比例）来评估机制的成功程度，作为 NP-难的包容性理由问题的解决方案。报告的实验描述了创造力率、推荐规模、论证密度和人口规模如何影响覆盖率和语料库多样性。在已验证的选民群体中，女巫攻击不可行且仅关系图可被操纵，我们通过协同策略性投票攻击对评分进行压力测试：标签洪泛攻击会降低覆盖率，而基于作者计数的反向 PageRank 规则关系加权在抵抗洪泛方面显著优于均匀加权。