当代理人意见不一致：多代理LLM流水线中的选择瓶颈
When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines
AI总结：
本文研究多代理LLM流水线中团队多样性对输出质量的影响，提出选择瓶颈概念，通过数学公式确定多样性帮助或损害的临界点，并通过实验验证选择机制的重要性。
摘要：
多代理LLM流水线在团队多样性是否提升输出质量上产生矛盾证据：异质混合代理团队优于单模型，但同质Self-MoA团队在基于合成的聚合下始终获胜。我们通过识别选择瓶颈——聚合质量中的交叉阈值来解决这一问题，该阈值决定多样性是否有助于输出。在此模型下，我们获得一个闭式交叉阈值s*（命题1），将帮助和损害的 regime 分开。在涵盖42个任务的42个任务（N=210）的针对性实验中，一个具有基于裁判选择的多样化团队在单模型基线上的胜率高达0.810，而同质团队得分为0.512——接近随机（Glass的Δ=2.07）。基于裁判的选择方法在基于MoA的合成方法上表现更好，Δ_WR=+0.631——合成方法在零个任务中被裁判小组偏好。独立裁判的解耦评估证实了所有方向性的发现（Spearman ρ=0.90）。探索性证据表明，加入较弱的模型可以提高性能并降低成本（p < 10^{-4}，非预先注册）。我们的结果表明，在单轮生成-选择流水线中，选择器质量可能比生成器多样性更具影响。
英文摘要：
Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality: heterogeneous Mixture-of-Agents teams outperform single models, yet homogeneous Self-MoA teams consistently win under synthesis-based aggregation. We propose a resolution by identifying the selection bottleneck -- a crossover threshold in aggregation quality that determines whether diversity helps or hurts. Under this model, we obtain a closed-form crossover threshold $s^*$ (Proposition 1) that separates the regimes where diversity helps and hurts. In a targeted experiment spanning 42 tasks across 7 categories ($N=210$), a diverse team with judge-based selection achieves a win rate of 0.810 against a single-model baseline, while a homogeneous team scores 0.512 -- near chance (Glass's $Δ= 2.07$). Judge-based selection outperforms MoA-style synthesis by $Δ_{\mathrm{WR}} = +0.631$ -- the synthesis approach is preferred over the baseline in zero of 42 tasks by the judge panel. A decoupled evaluation with independent judges confirms all directional findings (Spearman $ρ= 0.90$). Exploratory evidence suggests that including a weaker model improves performance while reducing cost ($p < 10^{-4}$, not pre-registered). Our results suggest that selector quality may be a more impactful design lever than generator diversity in single-round generate-then-select pipelines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
