[2505.08243] Training Strategies for Efficient Embodied Reasoning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack
View PDF HTML (experimental) Abstract:Robot chain-of-thought reasoning (CoT) -- wherein a model predicts helpful intermediate representations before choosing actions -- provides an effective method for improving the generalization and performance of robot policies, especially vision-language-action models (VLAs). While such approaches have been shown to improve performance and generalization, they suffer from core limitations, like needing specialized robot reasoning data and slow inference speeds. To design new robot reasoning approaches that address these issues, a more complete…
saved by
related reading
- Explore | alphaXivalphaxiv.org
- As Rocks May Think | Eric Jangevjang.com
- How Claude Performs on Robotics Tasks \ Anthropicanthropic.com
- DeepSeek-R1arxiv.org
- Explore | alphaXivalphaxiv.org
- RT-2: Vision-Language-Action Modelsrobotics-transformer2.github.io
- MolmoAct Action Reasoning Models that can Reason in Spacearxiv.org
- Vestigial reasoning in RL — LessWronglesswrong.com
- A VLA with Open-World Generalizationpi.website
- Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Controlsteerable-policies.github.io
- Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
- SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningalphaxiv.org