用基础模型构建多智能体系统，加速社会影响类AI研发
Towards Foundation-model-based Multiagent System to Accelerate AI for Social Impact
- 设计元级多智能体系统，统一处理社会影响问题的全流程
- 减少专家与研究人员的计算负担，提升开发效率
- 强调人机协同，确保技术应用的伦理与有效性
人工智能赋能社会影响（AI4SI）在公共卫生、农业、教育、保护和公共安全等领域具有巨大潜力。然而，现有研究通常耗时耗力且资源需求高，难以推广；标准做法是为特定问题定制基础系统。本文提出构建一种新型元级多智能体系统，旨在加速此类基础系统的开发，降低计算成本并减轻领域专家与AI研究者的负担。该方法基于基础模型与大语言模型，聚焦资源分配问题，贯穿从问题定义、方案设计到影响评估的全链条。同时，强调部署中的伦理挑战，并主张采用人机协同模式，确保AI系统的负责任、有效应用。
原文摘要 · Abstract (English)
AI for social impact (AI4SI) offers significant potential for addressing complex societal challenges in areas such as public health, agriculture, education, conservation, and public safety. However, existing AI4SI research is often labor-intensive and resource-demanding, limiting its accessibility and scalability; the standard approach is to design a (base-level) system tailored to a specific AI4SI problem. We propose the development of a novel meta-level multi-agent system designed to accelerate the development of such base-level systems, thereby reducing the computational cost and the burden on social impact domain experts and AI researchers. Leveraging advancements in foundation models and large language models, our proposed approach focuses on resource allocation problems providing help across the full AI4SI pipeline from problem formulation over solution design to impact evaluation. We highlight the ethical considerations and challenges inherent in deploying such systems and emphasize the importance of a human-in-the-loop approach to ensure the responsible and effective application of AI systems.
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。