JoyAgent-JDGenie: Technical Report on the GAIA
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914069780365312 |
|---|---|
| author | Liu, Jiarun Xu, Shiyue Liu, Shangkun Li, Yang Liu, Wen Liu, Min Zhou, Xiaoqing Wang, Hanmin Jia, Shilin Wang, zhen Tian, Shaohua Li, Hanhao Zhang, Junbo Yu, Yongli Cao, Peng Wang, Haofen |
| author_facet | Liu, Jiarun Xu, Shiyue Liu, Shangkun Li, Yang Liu, Wen Liu, Min Zhou, Xiaoqing Wang, Hanmin Jia, Shilin Wang, zhen Tian, Shaohua Li, Hanhao Zhang, Junbo Yu, Yongli Cao, Peng Wang, Haofen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00510 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JoyAgent-JDGenie: Technical Report on the GAIA Liu, Jiarun Xu, Shiyue Liu, Shangkun Li, Yang Liu, Wen Liu, Min Zhou, Xiaoqing Wang, Hanmin Jia, Shilin Wang, zhen Tian, Shaohua Li, Hanhao Zhang, Junbo Yu, Yongli Cao, Peng Wang, Haofen Computation and Language 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. |
| title | JoyAgent-JDGenie: Technical Report on the GAIA |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.00510 |