Is There Any Social Principle for LLM-Based Agents?
arXiv:2308.11136v26 citationsh-index: 10
Originality Synthesis-oriented
AI Analysis
This work addresses the need for foundational principles in AI agent research, though it is conceptual and incremental in nature.
The paper argues that research on LLM-based agents should move beyond human-centered alignment and applications to focus on the agents themselves, proposing the establishment of tailored social sciences for agents.
Focus on Large Language Model based agents should involve more than "human-centered" alignment or application. We argue that more attention should be paid to the agent itself and discuss the potential of establishing tailored social sciences for agents.