Reinforced Reasoning for Interactive Multi-step Embodied Planning

Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle in interactive environments. In this work, we introduce a reinforcement fine-tuning framework that brings R1-style reasoning enhancement into embodied planning. We adopt an offline reward paradigm to avoid costly online interaction, design a rule-based reward function tailored to multi-step action quality and optimize the policy via Generalized Reinforced Preference Optimization (GRPO). Our approach is evaluated on Embench, a recent benchmark for interactive embodied tasks, covering both in-domain and out-of-domain scenarios. Experimental results show that our method significantly outperforms models of similar or larger scale, including GPT-4o-mini and 70B+ open-source baselines, and exhibits strong generalization to unseen environments. This work highlights the potential of reinforcement-driven reasoning to advance multi-step planning in embodied AI.