Computational Recipe Intelligence: A Survey of Recipe Design, Generation, Recommendation, and Evaluation Protocols

Recent advances in artificial intelligence have transformed recipes from static textual artifacts into computational objects that support design, generation, and personalized recommendation. However, existing studies remain fragmented, typically addressing these tasks in isolation and lacking a unified analytical framework. This paper presents a comprehensive survey of recipe intelligence by systematically integrating recipe design, recipe generation, and recipe recommendation within a coherent computational framework. We review representative methods across these three tasks, including knowledge-based design systems, statistical and neural sequence generation models, cross-modal vision-language generation methods, pretraining- and retrieval-augmented generation approaches, and behavior-, context-, semantic-, and goal-driven recommendation methods. Particular attention is given to how these methods represent culinary knowledge, model user preferences, handle constraints, and support personalization. We further summarize commonly used datasets, data acquisition and processing strategies, and evaluation protocols, thereby clarifying the empirical foundations of current recipe intelligence research. Finally, we discuss key challenges and outline future directions toward unified, controllable, and interactive recipe intelligence systems.