We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuation with real-time, state-conditioned parameter decisions. At every $k$-th iteration, the LLM receives a structured observation$-$current compliance, grayness index, stagnation counter, checkerboard measure, volume fraction, and budget consumption$-$and outputs numerical values for the penalization exponent $p$, projection sharpness $β$, filter radius $r_{\min}$, and move limit $δ$ via a Direct Numeric Control interface. A hard grayness gate prevents premature binarization, and a meta-optimization loop uses a second LLM pass to tune the agent's call frequency and gate threshold across runs. We benchmark the agent against four baselines$-$fixed (no-continuation), standard three-field continuation, an expert heuristic, and a schedule-only ablation$-$on three 2-D problems (cantilever, MBB beam, L-bracket) at $120\!\times\!60$ resolution and two 3-D problems (cantilever, MBB beam) at $40\!\times\!20\!\times\!10$ resolution, all run for 300 iterations. A standardized 40-iteration sharpening tail is applied from the best valid snapshot so that compliance differences reflect only the exploration phase. The LLM agent achieves the lowest final compliance on every benchmark: $-5.7\%$ to $-18.1\%$ relative to the fixed baseline, with all solutions fully binary. The schedule-only ablation underperforms the fixed baseline on two of three problems, confirming that the LLM's real-time intervention$-$not the schedule geometry$-$drives the gain. Code and reproduction scripts will be released upon publication.

翻译：我们提出一个框架，其中大语言模型（LLM）作为SIMP拓扑优化的在线自适应控制器，将传统的固定调度连续策略替换为基于实时状态条件参数的决策过程。在每个第 $k$ 次迭代中，LLM接收结构化观测数据（当前柔顺度、灰度指数、停滞计数器、棋盘格度量、体积分数及预算消耗），并通过直接数字控制接口输出惩罚指数 $p$、投影锐度 $β$、滤波半径 $r_{\min}$ 和移动限制 $δ$ 的数值。硬灰度门控机制防止过早二值化，元优化循环通过第二次LLM调用调整智能体的调用频率和跨运行的门控阈值。我们在三个二维问题（悬臂梁、MBB梁、L形支架，分辨率 $120\times60$）和两个三维问题（悬臂梁、MBB梁，分辨率 $40\times20\times10$）上，将所提智能体与四种基准方法（无连续策略的固定法、标准三场连续法、专家启发式方法及仅调度消融法）进行对比，所有实验均运行300次迭代。从最优有效快照开始应用标准化的40次迭代锐化尾部，使柔顺度差异仅反映探索阶段。LLM智能体在所有基准测试中均达到最低最终柔顺度：相对固定基线降低 $-5.7\%$ 至 $-18.1\%$，且所有解完全二值化。仅调度消融法在三个问题中有两个表现不如固定基线，证实LLM的实时干预（而非调度几何结构）是性能提升的关键驱动因素。相关代码和复现脚本将在论文发表后公开。