发表机构
Virginia Tech; Advanced Research Computing, Virginia Tech（弗吉尼亚理工大学; 弗吉尼亚理工大学高级研究计算中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究一组大语言模型智能体在梅森-瓦茨实验中的网络效率效应，开发机械贝叶斯优化智能体作比较。计算实验表明，指示LLM智能体随机化首轮选择有显著网络效率效应，贝叶斯优化智能体收益更高，还比较了智能体多方面行为。
AI 中文摘要
集体解决问题通常要求小组成员在利用已知解决方案和探索新方案之间进行权衡，已知解决方案的信息可通过通信网络在个体成员之间传播。梅森-瓦茨实验表明，在二维搜索任务中，短路径网络中的人类小组比长路径网络中的小组表现更好。在这项工作中，我们专注于研究一组大语言模型（LLM）智能体情况下的这种网络效率效应。具体而言，我们让16个LLM智能体在8种梅森-瓦茨网络拓扑上进行该实验。此外，我们开发了机械贝叶斯优化智能体，以便将LLM智能体的性能与机械智能体和人类实验数据进行比较。我们的计算实验表明，当被指示随机化首轮选择时，LLM智能体显示出显著的网络效率效应，而在默认初始化下则不然。在这个实验中，添加一句首轮随机化指令可使集体收益提高超过八种网络拓扑估计收益差异的三倍。此外，在这个空间搜索任务中，贝叶斯优化智能体获得的收益高于被评估的LLM智能体。我们还进一步比较了智能体的探索-利用行为、复制和空间多样性。
英文摘要
Collective problem solving often requires that group members consider the tradeoff between exploitation of known solutions and exploration for new ones, where information of known solutions can be disseminated among individual members through communication networks. The Mason--Watts experiment (PNAS 2012) showed that human groups in shorter-path networks outperform those in longer-path networks on a two-dimensional search task. In this work, we focus on the investigation of such network-efficiency effects in the setting of a group of large language model (LLM) agents. Specifically, we consider groups of sixteen LLM agents playing the Mason--Watts experiment on the eight Mason--Watts network topologies. Moreover, we develop mechanistic Bayesian optimization agents such that the performance of LLM agents can be compared with both the mechanistic agents and the human experimental data. Our computational experiments indicate that the LLM agents show a significant network-efficiency effect when instructed to randomize their first-round choices, but not under the default initialization. In this experiment, adding a one-sentence first-round randomization instruction improves collective payoff by more than three times the estimated payoff difference across the eight network topologies. Also, the Bayesian optimization agents obtain higher payoffs than the evaluated LLM agents on this spatial search task. We further compare the agents' exploration--exploitation behavior, copying, and spatial diversity.
CommentsAccepted at ASONAM 2026; to appear in the Springer proceedings
