Towards Unified Alignment Between Agents, Humans, and Environment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914678591979520 |
|---|---|
| author | Yang, Zonghan Liu, An Liu, Zijun Liu, Kaiming Xiong, Fangzhou Wang, Yile Yang, Zeyuan Hu, Qingyuan Chen, Xinrui Zhang, Zhenhe Luo, Fuwen Guo, Zhicheng Li, Peng Liu, Yang |
| author_facet | Yang, Zonghan Liu, An Liu, Zijun Liu, Kaiming Xiong, Fangzhou Wang, Yile Yang, Zeyuan Hu, Qingyuan Chen, Xinrui Zhang, Zhenhe Luo, Fuwen Guo, Zhicheng Li, Peng Liu, Yang |
| contents | The rapid progress of foundation models has led to the prosperity of autonomous agents, which leverage the universal capabilities of foundation models to conduct reasoning, decision-making, and environmental interaction. However, the efficacy of agents remains limited when operating in intricate, realistic environments. In this work, we introduce the principles of $\mathbf{U}$nified $\mathbf{A}$lignment for $\mathbf{A}$gents ($\mathbf{UA}^2$), which advocate for the simultaneous alignment of agents with human intentions, environmental dynamics, and self-constraints such as the limitation of monetary budgets. From the perspective of $\mathbf{UA}^2$, we review the current agent research and highlight the neglected factors in existing agent benchmarks and method candidates. We also conduct proof-of-concept studies by introducing realistic features to WebShop, including user profiles to demonstrate intentions, personalized reranking for complex environmental dynamics, and runtime cost statistics to reflect self-constraints. We then follow the principles of $\mathbf{UA}^2$ to propose an initial design of our agent, and benchmark its performance with several candidate baselines in the retrofitted WebShop. The extensive experimental results further prove the importance of the principles of $\mathbf{UA}^2$. Our research sheds light on the next steps of autonomous agent research with improved general problem-solving abilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07744 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Unified Alignment Between Agents, Humans, and Environment Yang, Zonghan Liu, An Liu, Zijun Liu, Kaiming Xiong, Fangzhou Wang, Yile Yang, Zeyuan Hu, Qingyuan Chen, Xinrui Zhang, Zhenhe Luo, Fuwen Guo, Zhicheng Li, Peng Liu, Yang Artificial Intelligence Computation and Language Machine Learning The rapid progress of foundation models has led to the prosperity of autonomous agents, which leverage the universal capabilities of foundation models to conduct reasoning, decision-making, and environmental interaction. However, the efficacy of agents remains limited when operating in intricate, realistic environments. In this work, we introduce the principles of $\mathbf{U}$nified $\mathbf{A}$lignment for $\mathbf{A}$gents ($\mathbf{UA}^2$), which advocate for the simultaneous alignment of agents with human intentions, environmental dynamics, and self-constraints such as the limitation of monetary budgets. From the perspective of $\mathbf{UA}^2$, we review the current agent research and highlight the neglected factors in existing agent benchmarks and method candidates. We also conduct proof-of-concept studies by introducing realistic features to WebShop, including user profiles to demonstrate intentions, personalized reranking for complex environmental dynamics, and runtime cost statistics to reflect self-constraints. We then follow the principles of $\mathbf{UA}^2$ to propose an initial design of our agent, and benchmark its performance with several candidate baselines in the retrofitted WebShop. The extensive experimental results further prove the importance of the principles of $\mathbf{UA}^2$. Our research sheds light on the next steps of autonomous agent research with improved general problem-solving abilities. |
| title | Towards Unified Alignment Between Agents, Humans, and Environment |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2402.07744 |