PreAct: Prediction Enhances Agent's Planning Ability
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917857382629376 |
|---|---|
| author | Fu, Dayuan Huang, Jianzhao Lu, Siyuan Dong, Guanting Wang, Yejie He, Keqing Xu, Weiran |
| author_facet | Fu, Dayuan Huang, Jianzhao Lu, Siyuan Dong, Guanting Wang, Yejie He, Keqing Xu, Weiran |
| contents | Addressing the disparity between forecasts and actual results can enable individuals to expand their thought processes and stimulate self-reflection, thus promoting accurate planning. In this research, we present **PreAct**, an agent framework that integrates **pre**diction, **rea**soning, and **act**ion. By utilizing the information derived from predictions, the large language model (LLM) agent can provide a wider range and more strategically focused reasoning. This leads to more efficient actions that aid the agent in accomplishing intricate tasks. Our experimental results show that PreAct surpasses the ReAct method in completing complex tasks and that PreAct's performance can be further improved when paired with other memory or selection strategy techniques. We presented the model with varying quantities of historical predictions and discovered that these predictions consistently enhance LLM planning.The variances in single-step reasoning between PreAct and ReAct indicate that PreAct indeed has benefits in terms of diversity and strategic orientation over ReAct. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11534 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PreAct: Prediction Enhances Agent's Planning Ability Fu, Dayuan Huang, Jianzhao Lu, Siyuan Dong, Guanting Wang, Yejie He, Keqing Xu, Weiran Computation and Language Artificial Intelligence Addressing the disparity between forecasts and actual results can enable individuals to expand their thought processes and stimulate self-reflection, thus promoting accurate planning. In this research, we present **PreAct**, an agent framework that integrates **pre**diction, **rea**soning, and **act**ion. By utilizing the information derived from predictions, the large language model (LLM) agent can provide a wider range and more strategically focused reasoning. This leads to more efficient actions that aid the agent in accomplishing intricate tasks. Our experimental results show that PreAct surpasses the ReAct method in completing complex tasks and that PreAct's performance can be further improved when paired with other memory or selection strategy techniques. We presented the model with varying quantities of historical predictions and discovered that these predictions consistently enhance LLM planning.The variances in single-step reasoning between PreAct and ReAct indicate that PreAct indeed has benefits in terms of diversity and strategic orientation over ReAct. |
| title | PreAct: Prediction Enhances Agent's Planning Ability |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.11534 |