[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

• Dhruv Gautam

related reading

• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningalphaxiv.org
• [2412.06769] Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2510.27338] Reasoning Models Sometimes Output Illegible Chains of Thoughtarxiv.org
• Chain of Draft: Thinking Faster by Writing Lessarxiv.org
• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
• A VLA that Learns from Experiencepi.website
• [2602.10556] LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transferarxiv.org
• Precise Manipulation with Efficient Online RLpi.website
• LLM Post-Training: A Deep Dive into Reasoning Large Language Modelsarxiv.org
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2505.05410] Reasoning Models Don't Always Say What They Thinkarxiv.org