While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address this, we introduce ManiAgent, an agentic architecture for general manipulation tasks that achieves end-to-end output from task descriptions and environmental inputs to robotic manipulation actions. In this framework, multiple agents involve inter-agent communication to perform environmental perception, sub-task decomposition and action generation, enabling efficient handling of complex manipulation scenarios. Evaluations show ManiAgent achieves an 86.8% success rate on the SimplerEnv benchmark and 95.8% on real-world pick-and-place tasks, enabling efficient data collection that yields VLA models with performance comparable to those trained on human-annotated datasets. The project webpage is available at https://yi-yang929.github.io/ManiAgent/.
@article{arxiv.2510.11660,
title = {ManiAgent: An Agentic Framework for General Robotic Manipulation},
author = {Yi Yang and Kefan Gu and Yuqing Wen and Hebei Li and Yucheng Zhao and Tiancai Wang and Xudong Liu},
journal= {arXiv preprint arXiv:2510.11660},
year = {2025}
}