轨迹预测是自动驾驶系统的关键组成部分，因为未来运动直接影响碰撞检测、行为规划与控制。该任务在密集交互、异质行为、多模态未来以及车载计算资源受限等条件下仍具挑战性。现有基于图、注意力机制和生成式的方法虽提升了交互推理或不确定性建模能力，但其高容量设计往往难以满足实时部署需求。轻量级预测器及传统蒸馏方法虽可降低推理开销，却通常依赖静态模仿，且未显式校正与安全性相关联的教师模型偏差。本文提出\textbf{MAVEN-T}，一种面向实时多智能体轨迹预测的强化异构蒸馏框架。其中，高容量教师模型采用具备环视感知能力的图编码器建模有向局部交互，结合高效时序滤波与移窗空间注意力机制，并通过稀疏混合专家（Mixture-of-Experts）解码头输出特定驾驶意图的未来轨迹；紧凑型学生模型基于GRU与Squeeze-and-Excitation模块构建，并配备低秩适配（Low-Rank Adapted）策略头，通过特征级、注意力级与语义级蒸馏进行训练。为进一步使预测结果契合下游行为需求，学生模型进一步利用近端策略优化（Proximal Policy Optimization）奖励进行微调，奖励信号涵盖避撞、乘坐舒适性与行驶进展；同时，复杂度感知的课程学习（complexity-aware curriculum）与弹性权重固化（Elastic Weight Consolidation）保障了分阶段训练的稳定性。实验在NGSIM、HighD、MoCAD、Argoverse~2及Waymo Open Motion数据集上评估了所提方法在精度、效率、泛化性、鲁棒性及闭环安全性方面的表现。学生模型实现6.2$\times$参数压缩、3.7$\times$推理加速，并在NVIDIA Jetson AGX Orin平台上达到14.6 ms延迟，同时保持具有竞争力的预测精度。

Trajectory prediction is a key component of autonomous driving systems because future motions directly affect collision checking, behavior planning, and control. The task remains challenging under dense interactions, heterogeneous behaviors, multimodal futures, and limited on-board computation. Existing graph, attention, and generative predictors improve interaction reasoning or uncertainty modeling, but their high-capacity designs are often costly for real-time deployment. Lightweight predictors and conventional distillation reduce inference cost, yet usually rely on static imitation and do not explicitly correct safety-relevant teacher bias. This paper proposes \textbf{MAVEN-T}, a reinforced heterogeneous distillation framework for real-time multi-agent trajectory prediction. A high-capacity teacher models directed local interactions with a surround-aware graph encoder, combines efficient temporal filtering with shifted-window spatial attention, and decodes maneuver-specific futures through a sparse Mixture-of-Experts head. A compact GRU--Squeeze-and-Excitation student with a Low-Rank Adapted policy head is trained by feature-, attention-, and semantic-level distillation. To align prediction with downstream behavior, the student is further refined by Proximal Policy Optimization rewards for collision avoidance, comfort, and progress, while a complexity-aware curriculum and Elastic Weight Consolidation stabilize stage-wise training. Experiments on NGSIM, HighD, MoCAD, Argoverse~2, and the Waymo Open Motion Dataset evaluate accuracy, efficiency, generalization, robustness, and closed-loop safety. The student achieves 6.2$\times$ parameter compression, 3.7$\times$ inference acceleration, and 14.6,ms latency on an NVIDIA Jetson AGX Orin while maintaining competitive accuracy.