AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910459519565824 |
|---|---|
| author | Qiao, Shuofei Zhang, Ningyu Fang, Runnan Luo, Yujie Zhou, Wangchunshu Jiang, Yuchen Eleanor Lv, Chengfei Chen, Huajun |
| author_facet | Qiao, Shuofei Zhang, Ningyu Fang, Runnan Luo, Yujie Zhou, Wangchunshu Jiang, Yuchen Eleanor Lv, Chengfei Chen, Huajun |
| contents | Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework for QA that does not rely on large-scale annotated data and synthetic planning trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. Further analysis demonstrates the effectiveness of the division-of-labor strategy, with the trajectory quality generated by AutoAct generally outperforming that of others. Code will be available at https://github.com/zjunlp/AutoAct. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05268 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning Qiao, Shuofei Zhang, Ningyu Fang, Runnan Luo, Yujie Zhou, Wangchunshu Jiang, Yuchen Eleanor Lv, Chengfei Chen, Huajun Computation and Language Artificial Intelligence Human-Computer Interaction Machine Learning Multiagent Systems Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework for QA that does not rely on large-scale annotated data and synthetic planning trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. Further analysis demonstrates the effectiveness of the division-of-labor strategy, with the trajectory quality generated by AutoAct generally outperforming that of others. Code will be available at https://github.com/zjunlp/AutoAct. |
| title | AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2401.05268 |