A review of collective agri-environmental schemes using a human–AI framework

We systematically review collective agri-environmental schemes that support landscape stewardship in agriculture. We analyze 96 case studies across OECD countries based on 73 peer-reviewed articles. To guide this review, we develop a framework based on policy dimensions, the policy cycle, and micro-level implementation dimensions. This framework provides a basis for defining evaluation criteria and for assessing how these schemes are designed. The review combines the analytical power of artificial intelligence with expert domain knowledge. The synthesis of both enables a comprehensive examination of policy and implementation dimensions, resulting in critical insights into the schemes’ designs and functioning, and their broader applicability. Our results describe patterns of design and implementation in the reviewed literature, without establishing a causal link between the design and implementation of schemes and ecological outcomes. We find considerable heterogeneity among schemes indicating flexibility for decision-makers to adapt schemes to specific environmental targets at local scale, but that there is still significant room to enhance the role of farmers as key players in collective agri-environmental schemes. By integrating human expertise with the capabilities of large language models, our approach exemplifies how to balance and mitigate the limitations of each, increasing the transparency of the review process.