Scientific idea generation is central to discovery, requiring the joint satisfaction of novelty and scientific soundness. Unlike standard reasoning or general creative generation, scientific ideation is inherently open-ended and multi-objective, making its automation particularly challenging. Recent advances in large language models (LLMs) have enabled the generation of coherent and plausible scientific ideas, yet the nature and limits of their creative capabilities remain poorly understood. This survey provides a structured synthesis of methods for LLM-driven scientific ideation, focusing on how different approaches trade off novelty and scientific validity. We organize existing methods into five complementary families: External knowledge augmentation, Prompt-based distributional steering, Inference-time scaling, Multi-agent collaboration, and Parameter-level adaptation. To interpret their contributions, we adopt two complementary creativity frameworks: Boden taxonomy to characterize the expected level of creative novelty, and Rhodes 4Ps framework to analyze the aspects or sources of creativity emphasized by each method. By aligning methodological developments with cognitive creativity frameworks, this survey clarifies the evaluation landscape and identifies key challenges and directions for reliable and systematic LLM-based scientific discovery.

翻译：科学创意生成是科学发现的核心，需要同时满足新颖性与科学严谨性。与标准推理或一般创造性生成不同，科学构思本质上是开放式的、多目标的，这使得其自动化尤为困难。大型语言模型（LLMs）的最新进展已能够生成连贯且看似合理的科学创意，然而其创造性能力的本质与局限仍鲜为人知。本综述对LLM驱动的科学构思方法进行了结构化梳理，重点关注不同方法如何权衡新颖性与科学有效性。我们将现有方法归纳为五个互补的类别：外部知识增强、基于提示的分布导向、推理时缩放、多智能体协作以及参数级适应。为阐释其贡献，我们采用两个互补的创造力框架：Boden分类法用于表征预期的创造性新颖度层次，Rhodes 4Ps框架用于分析各方法所强调的创造力维度或来源。通过将方法论进展与认知创造力框架相结合，本综述厘清了评估现状，并指出了实现可靠、系统化的基于LLM的科学发现所面临的关键挑战与未来方向。