Trained on diverse human-authored texts, Large Language Models (LLMs) unlocked the potential for Creative Natural Language Generation (CNLG), benefiting various applications like advertising and storytelling. Nevertheless, CNLG still remains difficult due to two main challenges. (1) Multi-objective flexibility: user requirements are often personalized, fine-grained, and pluralistic, which LLMs struggle to satisfy simultaneously; (2) Interpretive complexity: beyond generation, creativity also involves understanding and interpreting implicit meaning to enhance users' perception. These challenges significantly limit current methods, especially in short-form text generation, in generating creative and insightful content. To address this, we focus on Chinese baby naming, a representative short-form CNLG task requiring adherence to explicit user constraints (e.g., length, semantics, anthroponymy) while offering meaningful aesthetic explanations. We propose NAMeGEn, a novel multi-agent optimization framework that iteratively alternates between objective extraction, name generation, and evaluation to meet diverse requirements and generate accurate explanations. To support this task, we further construct a classical Chinese poetry corpus with 17k+ poems to enhance aesthetics, and introduce CBNames, a new benchmark with tailored metrics. Extensive experiments demonstrate that NAMeGEn effectively generates creative names that meet diverse, personalized requirements while providing meaningful explanations, outperforming six baseline methods spanning various LLM backbones without any training.

翻译：大型语言模型（LLMs）在多样化的人类撰写文本上进行训练，释放了创意自然语言生成（CNLG）的潜力，为广告和故事叙述等应用带来了益处。然而，CNLG仍然面临两大主要挑战：（1）多目标灵活性：用户需求通常是个性化、细粒度且多元的，LLMs难以同时满足；（2）解释复杂性：除了生成之外，创意还涉及理解和阐释隐含意义以增强用户的感知。这些挑战显著限制了现有方法在生成创意且富有洞察力内容方面的能力，尤其是在短文本生成领域。为解决这一问题，我们聚焦于中文婴儿命名这一代表性的短文本CNLG任务，该任务要求在遵循明确的用户约束（如长度、语义、人名学）的同时，提供具有美学意义的解释。我们提出了NAMeGEn，一种新颖的多智能体优化框架，通过迭代交替进行目标提取、命名生成和评估，以满足多样化需求并生成准确的解释。为支持此任务，我们进一步构建了一个包含17,000多首古诗的古典诗歌语料库以增强美学性，并引入了CBNames这一配备定制化指标的新基准。大量实验表明，NAMeGEn能够有效生成满足多样化、个性化需求的创意名称，并提供有意义的解释，在无需任何训练的情况下，超越了涵盖多种LLM基线的六种基准方法。