# ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving

arXiv: https://arxiv.org/abs/2606.14058 · HTML: https://mlsanity.com/paper/2606.14058/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 13 of its 75 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)
- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)

## Builds on (most cited first, 13 of 13)

- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion](https://mlsanity.com/paper/2306.03083/) (2023)
- [Guided Conditional Diffusion for Controllable Traffic Simulation](https://mlsanity.com/paper/2210.17366/) (2022)
- [Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research](https://mlsanity.com/paper/2310.08710/) (2023)
- [TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction](https://mlsanity.com/paper/2303.04116/) (2023)
- [ReSim: Reliable World Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.09981/) (2025)
- [SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries](https://mlsanity.com/paper/2401.00391/) (2023)
- [Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments](https://mlsanity.com/paper/2503.22496/) (2025)
- [SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model](https://mlsanity.com/paper/2506.21976/) (2025)
- [Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model](https://mlsanity.com/paper/2412.09647/) (2024)
- [UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving](https://mlsanity.com/paper/2511.09013/) (2025)
- [EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial Representations](https://mlsanity.com/paper/2504.05422/) (2025)

## Built on by (most cited first, 2 of 2)

- [DriveCache: Action-Aware Caching for Driving World Model Inference](https://mlsanity.com/paper/2608.16354/) (2026)
- [From Generation to Simulation: How Far Are World Models from Being True Simulators?](https://mlsanity.com/paper/2608.23070/) (2026)

## Abstract (arXiv)

Reactive capability is a key property of data-driven behavior world model simulators for autonomous driving simulation systems. With this capability, simulated world agents can respond feasibly to autonomous vehicle (AV) behaviors that differ from the log. However, existing behavior simulation benchmarks do not directly measure reactive capability. They often let the simulator jointly control the AV and surrounding agents and evaluate realism through log similarity or open-loop prediction metrics. In this work, we introduce ReactSim-Bench for evaluating the reactive capability of behavior world model simulation in autonomous driving. We decouple the control of agents and the AV, using AV behaviors that differ from the log and require agents to respond as independent AV inputs. To obtain these AV behaviors, we construct a pipeline that uses an AV planner model to generate candidate behaviors and filters the data using rules and manual verification. Collision metrics, map-based metrics, and kinematic feasibility metrics are used to evaluate the safety and rule compliance of reactive responses. We construct 2,636 test scenarios with three categories and conduct a systematic evaluation of state-of-the-art models across multiple architectures, including Transformer-based, diffusion-based, and next-token-prediction-based models. We further analyze how replan frequency affects performance and provide insights for future studies.