Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Data-driven traffic simulation
Simulates realistic multi-agent driving behavior with learned models and large-scale scenario platforms.
36 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2019–2026) · an approach in Human-AI and goal-conditioned, keyword cluster “navigation · prediction · embodied”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
11 papers in 2023–24 and 20 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 3.7% to 5.2%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2019 · TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents (AAAI 2019 · 419 citations)
- 2021 · TrafficSim: Learning To Simulate Realistic Multi-Agent Behaviors (CVPR 2021 · 195 citations)
- 2022 · Learning From All Vehicles (CVPR 2022 · 187 citations)
- 2023 · Planning-Oriented Autonomous Driving (CVPR 2023 · 896 citations)
- 2024 · Feedback-Guided Autonomous Driving (CVPR 2024 · 18 citations)
- 2025 · End-to-End Autonomous Driving Through V2X Cooperation (AAAI 2025 · 42 citations)
- 2026 · UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving (AAAI 2026 · 2 citations)
Earliest papers here
- TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents (AAAI 2019 · 419 citations)
- Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions (CVPR 2019 · 288 citations)
- TrafficSim: Learning To Simulate Realistic Multi-Agent Behaviors (CVPR 2021 · 195 citations)
What has been tried
23 papers here report 220 measured changes (a component added, removed or swapped, compared with a baseline): helped 80%, no clear effect 3%, hurt 15%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add agent fusion | DAIR-V2X agent perception · mAP (%) | 16.5 -> 29.5 | Helped | End-to-End Autonomous Driving Through V2X Cooperation (AAAI 2025 · 42 citations) |
| Add language-based feedback fine-tuning | CARLA LAV · Driving Score | 72.45 -> 81.60 | Helped | Feedback-Guided Autonomous Driving (CVPR 2024 · 18 citations) |
| Add road vector tokenization | WOMD validation, trained on WOMD versus NuPlan · interactive | WOMD: 0.827 -> 0.807; NuPlan: 0.593 -> 0.696 | Mixed | SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction (NeurIPS 2024 · 12 citations) |
| add contingency cost learning | nuPlan · CLS | -2.9% CLS | Helped | Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving (NeurIPS 2024 · 10 citations) |
| increase patch size from 1 to 10 time steps | WOMD validation · REALISM | 0.6783 -> 0.7335 | Helped | BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction (NeurIPS 2024 · 8 citations) |
| Continue fine-tuning with BC | WOSAC 2% validation split · RMM | 0.7581 -> 0.7590 | No clear effect | Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models (CVPR 2025 · 7 citations) |
| Add VAE augmentation | pNEUMA, 20 seconds · Position RMSE (m) | 21.62±0.54 -> 19.21±0.44 | Helped | LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation (CVPR 2024 · 5 citations) |
| Use 10 replan steps instead of 40 | WOMD-XLMap, 60s rollout · Composite JS divergence | 0.2423 -> 0.1867 | Helped | SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model (CVPR 2025 · 3 citations) |
| add intra-timestep conditioning | full-control rollouts · collision rate | Helped | Trajeglish: Traffic Modeling as Next-Token Prediction (ICLR 2024 · 1 citation) | |
| jointly train with NTP and LFR rather than LFR alone | WOMD validation split · Prediction minADE | 0.6668 -> 0.6508 | Helped | UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning (NeurIPS 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 11 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- nuScenes · 2 of 11 papers
- Waymo Open Motion Dataset (WOMD) · 2 of 11 papers
Baselines
- Early Fusion · 3 of 11 papers
- Late Fusion · 3 of 11 papers
- V2X-ViT · 3 of 11 papers
- Where2comm · 3 of 11 papers
- CoBEVT · 3 of 11 papers
- No Fusion · 2 of 11 papers
- ReCogDrive · 2 of 11 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 31 papers; from OpenAlex and the papers' affiliations).
- The University of Hong Kong · 2 papers
- University of Science and Technology Beijing · 2 papers
- Tsinghua University · 2 papers
- University of Toronto · 2 papers
- SenseTime · 2 papers
- Waymo LLC · 2 papers
- Waymo · 2 papers
- Google · 2 papers
- Waymo Research · 2 papers
- University of Oxford · 2 papers
Use it
Download BibTeX of 29 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Embodied agent learning (93 papers)
- Interactive multi-agent trajectory prediction (75 papers)
- Vision-language navigation agents (66 papers)
Elsewhere in the topic
- Human-AI coordination agents (125 papers)
- World-model-based agents (110 papers)
- Imitation and skill learning (100 papers)
- Language-grounded reinforcement agents (96 papers)
- Boundedly rational agent modeling (87 papers)
- Collaborative multi-agent perception (86 papers)
- Intrinsically motivated exploration (86 papers)
- Learning-guided MAPF search (73 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).