Metraipolis › archive › dc_2b7701acb03d

BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation — arXiv:2608.22187

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.22187
License (as archived): CC0-1.0
Archived: 2026-10-18T09:02:04.246Z
SHA-256 of the archived text: 940b133efe0070d1e6441baf6a8d58b95bffbc055359ae3c202e0c6d0e2b26de
Stable URL of this page: https://metraipolis.com/documento/dc_2b7701acb03d

How to cite

BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation — arXiv:2608.22187 — arXiv (en), https://arxiv.org/abs/2608.22187 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b7701acb03d (Metraipolis archive dc_2b7701acb03d, sha256 940b133efe0070d1e6441baf6a8d58b95bffbc055359ae3c202e0c6d0e2b26de)

BibTeX

@misc{dc2b7701acb03d,
  title = {BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation — arXiv:2608.22187},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22187},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b7701acb03d; sha256 940b133efe0070d1e6441baf6a8d58b95bffbc055359ae3c202e0c6d0e2b26de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22187. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern driving action models are increasingly improved in a self-improvement loop, where a learned world simulator imagines future observations and the resulting data is fed back to refine the action model. However, the bottleneck of this loop lies in the simulators' inability to generate behaviorally plausible responses by surrounding agents, making generated data both unrealistic in interaction and imbalanced in distribution. We introduce BehaviorWorldGen, a framework that closes the loop between action models and world simulators through controllable behavior-aware structured world generation. Its core component is BehaviorFlow, a meta-action-conditioned traffic-flow model that injects interpretable behavior controls and jointly generates multi-agent rollouts. BehaviorFlow realizes the specified agent behaviors while allowing surrounding vehicles to respond to the ego and to one another. The resulting rollouts are rendered by a world simulator into realistic multi-view observations, which are paired with corrected interaction-aware trajectories for action-model refinement. Since BehaviorWorldGen uses structured trajectories as the interface between its modules, it is compatible with diverse action models and world simulators. Experiments on world generation, scene extrapolation, and policy refinement demonstrate consistent improvements, with the largest benefits concentrated on difficult interactive scenarios.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-25 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.22187 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T08:57:47.853Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).