RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning

Published June 10, 2026 · Category: Robotics

Overview

arXiv:2510.14828v3 Announce Type: replace-cross Abstract: Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the success of large language models and vision language models based on Supervised Fine-Tuning (SFT) in planning tasks, they continue facing challenges in performing long-horizon manipulation tasks in complex real-world environments, owing to their restricted common sense and reasoning capabilities. Considering that aligning general-purpose vision language models to robotic planning tasks via supervised fine-tuning suffers from poor generalization and insufficient physical understanding, we propose RoboGPT-R1, a two-stage fine-tuning framework for embodied planning. In this framework, supervised training acquires foundational knowledge through expert sequences, followed by RL to address the model's shortcomings in visual-spatial understanding and reasoning. To achieve physical understanding and action sequence consistency in multi-step reasoning tasks, we design a rule-based reward function that simultaneously considers long-horizon performance and action constraint in the environment. The reasoning model, trained on Qwen2.5-VL-3B, significantly outperforms the larger-scale model, GPT-4o-mini, by 21.33% and surpasses other work trained on Qwen2.5-VL-7B by 20.33% on the EmbodiedBench benchmark.

Source

Originally published at arxiv.org.

Related Articles

• AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness
• Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models
• Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations