Studying how recommendation systems reshape social networks is difficult on live platforms: confounds abound, and controlled experiments risk user harm. We present an agent-based simulator where content production, tie formation, and a graph attention network (GAT) recommender co-evolve in a closed loop. We calibrate parameters using Mastodon data and validate out-of-sample against Bluesky (4--6\% error on structural metrics; 10--15\% on held-out temporal splits). Across 18 configurations at 100 agents, we find that \emph{activation timing} affects outcomes: introducing recommendations at $t=10$ vs.\ $t=40$ decreases transitivity by 10\% while engagement differs by $<$8\%. Delaying activation increases content diversity by 9\% while reducing modularity by 4\%. Scaling experiments ($n$ up to 5,000) show the effect persists but attenuates. Jacobian analysis confirms local stability under bounded reactance parameters. We release configuration schemas and reproduction scripts.

翻译：在真实社交平台上研究推荐系统如何重塑社交网络十分困难：混杂因素众多，且受控实验可能对用户造成损害。本文提出一种基于智能体的仿真框架，其中内容生产、关系形成与图注意力网络（GAT）推荐器在闭环中协同演化。我们使用Mastodon数据校准参数，并在Bluesky平台上进行样本外验证（结构指标误差为4-6%；时间划分验证误差为10-15%）。在100个智能体的18种配置实验中，发现激活时机对结果具有显著影响：在t=10时引入推荐系统相较于t=40时，传递性降低10%，而参与度差异小于8%。延迟激活可使内容多样性提升9%，同时模块性降低4%。扩展实验（n最大至5,000）表明该效应持续存在但逐渐衰减。雅可比矩阵分析证实了在有界反应参数下的局部稳定性。我们同步公开了配置架构与复现脚本。