Skip to content
Hot storiesContinuously updated

研究者推出多智能体协作决策评测基准TandemBench

1 reports1 reporting sourcesUpdated 9 hours ago

Start here

AI overview

2026年11月5日,研究人员在arXiv发布多智能体协作决策评测基准TandemBench。该基准包含1,200道多智能体烹饪题目,研究团队据此评测了40个原生决策模型与10个通用语言模型。测试结果显示,表现最佳的原生决策模型取得了62.50%的决策准确率,但在最优性验证能力上接近随机水平,经常错误判断候选方案之外是否存在更优解。目前,该基准的数据集与评估代码已公开发布。

AI-generated from reports · Updated 9 hours ago

Report timeline

Follow the reports to see different sides of the story.

Nov 5
  1. arXiv 自然语言处理
    TandemBench:多智能体协作决策模型评测基准

    研究人员推出包含 1,200 道多智能体烹饪题目的协作评测基准 TandemBench,并评测了 40 个原生决策模型与 10 个通用语言模型。测试显示最佳原生决策模型取得 62.50% 的决策准确率,但在最优性验证上接近随机水平,常错误判断候选方案外是否存在更优解。该基准的数据集与评估代码已公开发布。

Story heat trend

Current heat 8·Comparable peak 10(Nov 5 14:00)·Comparable change, last 24 hours–

02.557.510Nov5Nov5Nov5Nov5

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.