发表机构
Rensselaer Polytechnic Institute（伦斯勒理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SimTIO提出一种仿真支撑的多智能体大语言模型框架，通过组合信号控制等干预措施并基于仿真反馈优化，在约束全网性能下平均降低9.18%的瓶颈时间损失，支持LLM作为受约束的局部搜索算子。
AI 中文摘要
交通分析师必须将诊断出的瓶颈转化为可执行的干预措施，同时避免局部改进损害整个路网性能。本研究提出SimTIO，一种仿真支撑的多智能体大语言模型框架，用于在明确运行约束下组合和选择交通干预措施。SimTIO首先模拟一个未修改的SUMO场景，以识别一组基线固定的十条瓶颈路段。随后，一个基于实测的采样器初始化信号控制、走廊限速和需求保持路由动作，而三个专家智能体利用实测仿真反馈，从验证器确认的变异目录中选择单参数改进。兼容的动作被组合并重新仿真，以实测而非推断其交互效应。最终选择在约束全网延误、邻路溢出、通行能力损失和传送事件的同时最小化瓶颈时间损失，并将未修改场景保留为不操作（弃权）保护。在涵盖五个美国城市路网、三个合成需求种子及每个场景2400次起讫出行的15个案例中，SimTIO将前十瓶颈时间损失平均降低9.18%，全网延误降低2.78%。在相同的七次仿真预算下，它在86.7%的案例中找到了可行的改进方案，而基于实测的随机搜索为73.3%，确定性启发式方法为80.0%，尽管前十改进的差异在统计上不显著。这些结果支持将大语言模型用作受约束、反馈引导的局部搜索算子，同时将最终决策权保留给可执行工具、微观仿真和明确的安全约束。
英文摘要
Traffic analysts must translate diagnosed bottlenecks into executable interventions without allowing local improvements to degrade network-wide performance. This study presents SimTIO, a simulation-grounded multi-agent large language model framework for composing and selecting traffic interventions under explicit operational constraints. SimTIO first simulates an unmodified SUMO scenario to identify a baseline-frozen set of ten bottleneck edges. A grounded sampler then initializes signal-control, corridor-speed, and demand-preserving routing actions, while three specialist agents use measured simulation feedback to select one-parameter refinements from validator-confirmed mutation catalogs. Compatible actions are combined and re-simulated so that their interaction effects are measured rather than inferred. Final selection minimizes bottleneck time loss while constraining network-wide delay, neighboring-road spillover, throughput loss, and teleport events, with the unmodified scenario retained as a no-operation guard. Across 15 cases covering five U.S. urban networks, three synthetic-demand seeds, and 2,400 origin-destination trips per scenario, SimTIO reduced Top-10 bottleneck time loss by an average of 9.18 percent and network-wide delay by 2.78 percent. It found a feasible improving plan in 86.7 percent of cases, compared with 73.3 percent for grounded random search and 80.0 percent for a deterministic heuristic under the same seven-simulation budget, although the differences in Top-10 improvement were not statistically significant. These results support using LLMs as constrained, feedback-guided local search operators while reserving final decision authority for executable tools, microscopic simulation, and explicit safety constraints.
