发表机构
Institute of Medical Informatics, Otto-von-Guericke University Magdeburg（马格德堡奥托·冯·格里克大学医学信息学研究所）
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2026年FIFA世界杯56场比赛的实时评估，发现新闻专家在预测效用上优于定量专家并追平博彩市场，而多智能体综合未能超越最强专家。
AI 中文摘要
大型语言模型正被组织成具有专业化角色的多智能体系统，但这种专业化是否会产生不同的预测，以及随后的综合是否能提高效用，仍不清楚。在本研究中，我们对信息密集的2026年FIFA世界杯最后56场比赛进行了一项实时的前瞻性评估，保持前沿基础模型不变，同时赋予两个主要预测智能体对比鲜明的专业角色：一个专注于结构化表现统计的定量专家，以及一个专注于当前伤病、战术和新闻发布会信息的新闻专家。他们的预测随后由独立的评论员进行审查，再由一个元智能体进行整合，形成顺序的四智能体模型。博彩市场的预测作为外部基准。新闻专家获得了最高的平均概率加权前三名效用，并在前三名精确比分命中数上与博彩市场持平。然而，两个专业预测者在56场比赛中的50场中，至少就三个比分中的两个达成一致，且元智能体从未生成超过一个超出专家预测集的比分。这些发现表明，快速变化的非结构化信息可以连同结构化统计提供有价值的预测信号，而添加评论员和元智能体阶段并不一定产生互补信息或优于最强专家。
英文摘要
Large language models are being organized into multi-agent systems with specialized roles, but whether such specialization produces distinct forecasts and whether subsequent synthesis improves utility remains unclear. In this study, we carried out a live, prospective evaluation over the final 56 matches of the information-dense 2026 FIFA World Cup, keeping a frontier foundation model constant while assigning two primary forecasting agents contrasting specialist roles: a quantitative specialist focusing on structured performance statistics and a news specialist focusing on current injuries, tactics and information from press conferences. Their forecasts were then reviewed by a separate critic before being combined by a meta-agent, resulting in a sequential four-agent model. Forecasts from the betting market served as an external benchmark. The news specialist obtained the highest mean probability-weighted Top-3 utility and matched the betting market in Top-3 exact-score hits. Nevertheless, the two specialist forecasters agreed on at least two of the three scorelines in 50 out of 56 matches, and the meta-agent never generated more than one scoreline outside the specialists' forecast set. These findings show that rapidly changing, unstructured information can provide a valuable forecasting signal alongside structured statistics, whereas adding critic and meta-agent stages does not necessarily create complementary information or improve on the strongest specialist.
Comments10 pages, 3 figures, 1 table
