KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
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_ | 1866910839641997312 |
|---|---|
| author | Zhu, Yuqi Qiao, Shuofei Ou, Yixin Deng, Shumin Lyu, Shiwei Shen, Yue Liang, Lei Gu, Jinjie Chen, Huajun Zhang, Ningyu |
| author_facet | Zhu, Yuqi Qiao, Shuofei Ou, Yixin Deng, Shumin Lyu, Shiwei Shen, Yue Liang, Lei Gu, Jinjie Chen, Huajun Zhang, Ningyu |
| contents | Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions. This inadequacy primarily stems from the lack of built-in action knowledge in language agents, which fails to effectively guide the planning trajectories during task solving and results in planning hallucination. To address this issue, we introduce KnowAgent, a novel approach designed to enhance the planning capabilities of LLMs by incorporating explicit action knowledge. Specifically, KnowAgent employs an action knowledge base and a knowledgeable self-learning strategy to constrain the action path during planning, enabling more reasonable trajectory synthesis, and thereby enhancing the planning performance of language agents. Experimental results on HotpotQA and ALFWorld based on various backbone models demonstrate that KnowAgent can achieve comparable or superior performance to existing baselines. Further analysis indicates the effectiveness of KnowAgent in terms of planning hallucinations mitigation. Code is available in https://github.com/zjunlp/KnowAgent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03101 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents Zhu, Yuqi Qiao, Shuofei Ou, Yixin Deng, Shumin Lyu, Shiwei Shen, Yue Liang, Lei Gu, Jinjie Chen, Huajun Zhang, Ningyu Computation and Language Artificial Intelligence Human-Computer Interaction Machine Learning Multiagent Systems Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions. This inadequacy primarily stems from the lack of built-in action knowledge in language agents, which fails to effectively guide the planning trajectories during task solving and results in planning hallucination. To address this issue, we introduce KnowAgent, a novel approach designed to enhance the planning capabilities of LLMs by incorporating explicit action knowledge. Specifically, KnowAgent employs an action knowledge base and a knowledgeable self-learning strategy to constrain the action path during planning, enabling more reasonable trajectory synthesis, and thereby enhancing the planning performance of language agents. Experimental results on HotpotQA and ALFWorld based on various backbone models demonstrate that KnowAgent can achieve comparable or superior performance to existing baselines. Further analysis indicates the effectiveness of KnowAgent in terms of planning hallucinations mitigation. Code is available in https://github.com/zjunlp/KnowAgent. |
| title | KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2403.03101 |