Microsoft Research Asia explores how values shape AI agent societies
In an article for Harvard Business Review's Chinese edition, Microsoft Research Asia senior researcher Xiaoyuan Yi describes the lab's "Societal AI" research direction: a controlled multi-agent sandbox called the Community of Interactive and Value-influenced Agents, where agents find jobs, earn and spend resources, communicate, gift resources, attack each other and even reproduce, letting researchers observe how value distributions change individual and collective behavior. The account says that when the Benevolence value was systematically weakened in 25% of agents, deception and attacks increased, resources were redistributed through predatory competition and the population steadily fell, reaching zero in extreme cases — an outcome the author labels an X-risk marked by autonomy, catastrophe and irreversibility. It also claims that injecting diverse values produced more complex social network structures, deeper discussions of societal topics and more varied governance principles, though no quantitative benchmarks or paper links are given.
It pushes AI safety debates from aligning a single model to the dynamics of multi-agent communities, suggesting the question becomes which values a model is aligned to.
自从2022年底ChatGPT发布以来，生成式人工智能取得了诸多突破。它通过了图灵测试、法学院和商学院的考试，甚至在某些创意性任务上展现了超越人类的能力。然而伴随着这些举世瞩目的突破，AI也为人类社会带来了诸如网络安全、虚假信息、深度伪造等风险。更有甚者，最近研究者观察到前沿的AI可能“假装”安全以避免被修改，或者是当被告知有新版本时，试图复制自己以避免被淘汰。这些新兴的、无法预知的风险被称为涌现性风险（Emergent Risk)。我们有必要从技术角度对这些风险进行管控和消除，这不仅仅是我们作为AI研究者需要承担的社会责任，更大的原因在于，过去十几年里AI的角色发生了显著的转变。
创建AI价值观罗盘
早期AI扮演的更多是单纯的工具性角色，服从人类的命令，完成单一、简单的具体任务。随着大语言模型的诞生，当下的AI系统日趋复杂，其角色转变为助手，辅助与协调人类工作以助力完成更加复杂的任务。如果继续向未来展望，我们认为可能进入第三种状态：未来社会也许不再只是“一个人使用一个 AI”，而是由大量人类和大量AI智能体共同构成的人机共生社会（Human-AI Symbiotic Society）。
#Microsoft Research Asia#Societal AI#Community of Interactive and Value-influenced Agents#Constitutional AI