Achieving general-purpose robotics requires empowering robots to adapt and evolve based on their environment and feedback. Traditional methods face limitations such as extensive training requirements, difficulties in cross-task generalization, and lack of interpretability. Prompt learning offers new opportunities for self-evolving robots without extensive training, but simply reflecting on past experiences. However, extracting meaningful insights from task successes and failures remains a challenge. To this end, we propose the evolvable embodied agent (EEAgent) framework, which leverages large vision-language models (VLMs) for better environmental interpretation and policy planning. To enhance reflection on past experiences, we propose a long short-term reflective optimization (LSTRO) mechanism that dynamically refines prompts based on both past experiences and newly learned lessons, facilitating continuous self-evolution, thereby enhancing overall task success rates. Evaluations on six VIMA-Bench tasks reveal that our approach sets a new state-of-the-art, notably outperforming baselines in complex scenarios.
@article{arxiv.2604.13533,
title = {Evolvable Embodied Agent for Robotic Manipulation via Long Short-Term Reflection and Optimization},
author = {Jianzong Wang and Botao Zhao and Yayun He and Junqing Peng and Xulong Zhang},
journal= {arXiv preprint arXiv:2604.13533},
year = {2026}
}
Comments
This work has been accepted for publication in the Proceedings of the 2026 International Joint Conference on Neural Networks (IJCNN 2026)