Flow-ERD: Agent-type Aware Flow Matching With Entropy-Regularized Distillation for Diverse Traffic Simulation

Abstract

Realistic and diverse traffic simulation is essential to autonomous driving development. Yet prevailing benchmarks predominantly reward realism, and recent methods have optimized accordingly, leaving diversity underexplored. We introduce Flow-ERD, a multi-agent simulator that pursues realism and diversity jointly. Its backbone, Agent-Type Aware Flow Matching (AFM), couples flow matching's multi-modal expressiveness with type-specific kinematic execution. It preserves fine-grained diversity while keeping motions consistent with each agent type. A second stage, Entropy-Regularized Distillation (ERD), fine-tunes the closed-loop rollout distribution with an entropy-regularized reverse-KL objective. This mitigates closed-loop covariate shift while explicitly preventing collapse onto high-density modes. We evaluate Flow-ERD with Cross-Pair Diversity and its validity-gated variant alongside standard realism scores. Validation experiments further show that tuning entropy regularization recovers most of the pretrained backbone's diversity while retaining realism gains. Flow-ERD ranks first in test-split realism on the Waymo Open Sim Agents Challenge (WOSAC) and dominates the validation realism--diversity Pareto front among reproducible baselines.