Large Language Models are increasingly deployed as autonomous agents for complex real-world tasks, yet existing systems often focus on isolated improvements without a unifying design for robustness and adaptability. We propose a generalist agent architecture that integrates three core components: a collective multi-agent framework combining planning and execution agents with critic model voting, a hierarchical memory system spanning working, semantic, and procedural layers, and a refined tool suite for search, code execution, and multimodal parsing. Evaluated on a comprehensive benchmark, our framework consistently outperforms open-source baselines and approaches the performance of proprietary systems. These results demonstrate the importance of system-level integration and highlight a path toward scalable, resilient, and adaptive AI assistants capable of operating across diverse domains and tasks.
@article{arxiv.2510.00510,
title = {JoyAgent-JDGenie: Technical Report on the GAIA},
author = {Jiarun Liu and Shiyue Xu and Shangkun Liu and Yang Li and Wen Liu and Min Liu and Xiaoqing Zhou and Hanmin Wang and Shilin Jia and zhen Wang and Shaohua Tian and Hanhao Li and Junbo Zhang and Yongli Yu and Peng Cao and Haofen Wang},
journal= {arXiv preprint arXiv:2510.00510},
year = {2025}
}