arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.07744cs.AIcs.CLcs.LG
收藏

迈向智能体、人类与环境的统一对齐

Towards Unified Alignment Between Agents, Humans, and Environment

Tsinghua University(清华大学);Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院)

Zonghan Yang, An Liu, Zijun Liu, Kaiming Liu, Fangzhou Xiong, Yile Wang, Zeyuan Yang, Qingyuan Hu, Xinrui Chen, Zhenhe Zhang, Fuwen Luo, Zhicheng Guo, Peng Li, Yang Liu

AI总结:

本文提出智能体统一对齐($\mathbf{UA}^2$)原则,主张智能体需同时对齐人类意图、环境动态与自我约束,并在改造后的WebShop中验证了该原则对提升智能体现实问题解决能力的重要性。

摘要:

基础模型的快速进展带来了自主智能体的繁荣,这些智能体利用基础模型的通用能力进行推理、决策和环境交互。然而,智能体在复杂、现实的环境中运行时,其效能仍然有限。在这项工作中,我们引入了智能体统一对齐($\mathbf{UA}^2$)原则,主张智能体应同时对齐人类意图、环境动态以及自我约束(如货币预算的限制)。从$\mathbf{UA}^2$的视角出发,我们回顾了当前的智能体研究,并强调了现有智能体基准和方法候选中被忽视的因素。我们还通过向WebShop引入现实特征进行了概念验证研究,包括用于展示意图的用户画像、用于复杂环境动态的个性化重排序,以及反映自我约束的运行时成本统计。随后,我们遵循$\mathbf{UA}^2$原则提出了智能体的初步设计,并在改造后的WebShop中将其性能与几个候选基线进行了基准测试。广泛的实验结果进一步证明了$\mathbf{UA}^2$原则的重要性。我们的研究为提升通用问题解决能力的自主智能体研究的下一步提供了启示。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑