Agent Alignment in Evolving Social Norms
This addresses the challenge of aligning AI agents with dynamic human values for applications in domains where social norms change, representing an incremental advancement over existing LLM alignment methods.
The paper tackles the problem of aligning AI agents with evolving social norms by proposing an evolutionary framework called EvolutionaryAgent, which transforms alignment into a survival-of-the-fittest process, resulting in agents that progressively better align with norms while maintaining task proficiency.
Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems primarily focuses on passively aligning LLMs through human intervention. However, agents possess characteristics like receiving environmental feedback and self-evolution, rendering the LLM alignment methods inadequate. In response, we propose an evolutionary framework for agent evolution and alignment, named EvolutionaryAgent, which transforms agent alignment into a process of evolution and selection under the principle of survival of the fittest. In an environment where social norms continuously evolve, agents better adapted to the current social norms will have a higher probability of survival and proliferation, while those inadequately aligned dwindle over time. Experimental results assessing the agents from multiple perspectives in aligning with social norms demonstrate that EvolutionaryAgent can align progressively better with the evolving social norms while maintaining its proficiency in general tasks. Effectiveness tests conducted on various open and closed-source LLMs as the foundation for agents also prove the applicability of our approach.