AI for Social Impact (AI4SI) has achieved compelling results in public health, conservation, and security, yet scaling these successes remains difficult due to a persistent deployment bottleneck. We characterize this bottleneck through three coupled gaps: observational scarcity resulting from limited or unreliable data; policy synthesis challenges involving combinatorial decisions and nonstationarity; and the friction of human-AI alignment when incorporating tacit expert knowledge and dynamic constraints. We argue that Generative AI offers a unified pathway to bridge these gaps. LLM agents assist in human-AI alignment by translating natural-language guidance into executable objectives and constraints for downstream planners, while diffusion models generate realistic synthetic data and support uncertainty-aware modeling to improve policy robustness and transfer across deployments. Together, these tools enable scalable, adaptable, and human-aligned AI systems for resource optimization in high-stakes settings.

翻译：社会影响人工智能（AI4SI）在公共卫生、环境保护和公共安全领域已取得显著成果，但由于持续存在的部署瓶颈，这些成果的规模化推广仍面临困难。我们通过三个相互关联的缺口来刻画这一瓶颈：因数据有限或不可靠导致的观测稀缺性；涉及组合决策与非平稳性的策略综合挑战；以及整合隐性专家知识与动态约束时人机协同的摩擦。我们认为，生成式人工智能为弥合这些缺口提供了统一路径。大语言模型智能体通过将自然语言指导转化为下游规划器的可执行目标与约束，协助实现人机协同；而扩散模型则能生成逼真的合成数据，并支持不确定性感知建模，从而提升策略的鲁棒性及跨部署场景的迁移能力。这些工具共同构建了可扩展、自适应且与人类目标对齐的人工智能系统，为高风险场景下的资源优化提供支持。