Towards Unified Alignment Between Agents, Humans, and Environment

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


引用 0|浏览17
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 𝐔nified 𝐀lignment for 𝐀gents (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 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 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 𝐔𝐀^2. Our research sheds light on the next steps of autonomous agent research with improved general problem-solving abilities.
AI 理解论文