Unlock the potential of reasoning in embodied intelligence for advancements in scalable, human-centric robotics and autonomous systems.
The 1st edition of the Reasoning in Scalable Embodied Intelligence (RISE) workshop at NeurIPS 2026 focuses on the critical role of reasoning in transitioning embodied AI agents from controlled laboratories to open-world deployment in robotics, autonomous driving, and interactive physical environments.
While advances in robot learning have significantly improved perception and control, robust real-world performance increasingly depends on reasoning: the ability to interpret context, infer latent structure, anticipate long-horizon consequences, and adapt to previously unseen situations.Despite rapid progress, key questions remain regarding how reasoning should be represented, learned, and integrated with world models to move toward general-purpose embodied agents.
RISE aims to bridge traditionally separate communities (machine learning, robotics, computer vision, and autonomous systems) around the shared challenges of learning to reason in real-world environments. We emphasize learning-based reasoning grounded in perception and action, exploring multimodal foundation models, generative simulation, and reinforcement learning.
The workshop invites researchers and practitioners to:
| Time | Session |
|---|---|
| 08:30 – 08:40 | Open remarks: workshop goals, scope, and open questions for reasoning-driven embodied decision-making |
| 08:40 – 09:20 | Invited Talk 1 + Q&A: reasoning in vision-language-action models and embodied foundation models Keynote |
| 09:20 – 10:00 | Invited Talk 2 + Q&A: multimodal reasoning benchmarks and evaluation for embodied agents Keynote |
| 10:00 – 10:20 | Coffee break |
| 10:20 – 11:00 | Invited Talk 3 + Q&A: world models, simulation, and generative prediction for planning Keynote |
| 11:00 – 11:30 | Contributed oral session: three selected papers, 10 minutes each plus Q&A, followed by paper award announcements Oral |
| 11:30 – 12:30 | Poster session: contributed papers and community discussion Posters |
| 12:30 – 13:30 | Lunch break |
| 13:30 – 14:10 | nuReasoning challenge session: winner announcement, benchmark takeaways, and lessons for evaluation Challenge |
| 14:10 – 14:50 | Invited Talk 4 + Q&A: reasoning for robot learning, reinforcement learning, and scalable decision-making Keynote |
| 14:50 – 15:30 | Invited Talk 5 + Q&A: reasoning from human data, interaction, demonstrations, and feedback Keynote |
| 15:30 – 15:50 | Coffee break |
| 15:50 – 16:30 | Invited Talk 6 + Q&A: safety, uncertainty, and deployment of reasoning-enabled embodied systems Keynote |
| 16:30 – 17:20 | Panel Discussion: Reasoning or Imitation? What Is Missing in Embodied Foundation Models? Panel |
| 17:20 – 17:30 | Closing remarks: open problems, lessons learned, and next steps |
Final schedule, room allocation, and speaker order will be announced closer to the workshop date.
RISE 2026 invites high-quality contributions on reasoning in embodied intelligence, and related topics outlined above.
Submit NowThe nuReasoning Challenge aims to develop autonomous driving agents that can robustly handle rare interactions and complex causal dependencies, going beyond average-case perception and planning. This open dataset and benchmark is inspired by Motional's nuScenes and nuPlan datasets and the NAVSIM end-to-end driving benchmark, but is specifically targeted at reasoning-intensive, long-tail driving scenarios
Top-performing submissions will be invited to present their findings at the workshop. Cash prizes will be awarded to the winners of the nuReasoning challenge. All materials, including the dataset, code, and evaluation scripts, will remain publicly available after the workshop to support continued research.
RISE 2026 welcomes sponsorship from industry, startups, and institutions interested in foundation models for reasoning in embodied intelligence.
For sponsorship opportunities, please contact: zhiyuh@ucla.edu.
