用管理代理调节激励，让自私智能体合作共赢。
Managing multiple agents by automatically adjusting incentives
- 引入管理代理动态分配激励，引导多智能体协作。
- 在供应链场景中，总奖励提升22.2%，各方收益均增长。
- 适合研究多智能体协同与激励机制的开发者和研究人员。
未来几年，人工智能代理将用于更复杂的决策，涉及多个群体。一个主要挑战是AI代理倾向于追求自身利益，而人类往往考虑长远整体利益。本文提出一种方法，通过引入管理代理来调节代理间互动，并为特定行为分配激励，使自利代理共同实现社会整体目标。我们在供应链管理问题上测试该框架，结果表明：（1）原始奖励提升22.2%；（2）代理自身奖励提升23.8%；（3）管理代理奖励提升20.1%。
原文摘要 · Abstract (English)
In the coming years, AI agents will be used for making more complex decisions, including in situations involving many different groups of people. One big challenge is that AI agent tends to act in its own interest, unlike humans who often think about what will be the best for everyone in the long run. In this paper, we explore a method to get self-interested agents to work towards goals that benefit society as a whole. We propose a method to add a manager agent to mediate agent interactions by assigning incentives to certain actions. We tested our method with a supply-chain management problem and showed that this framework (1) increases the raw reward by 22.2%, (2) increases the agents' reward by 23.8%, and (3) increases the manager's reward by 20.1%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。