Generative recommendation (GR) has shown strong potential for sequential recommendation in an end-to-end generation paradigm. However, existing GR models suffer from severe cold-start collapse: their recommendation accuracy on cold-start items can drop to near zero. Current solutions typically rely on retraining with cold-start interactions, which is hindered by sparse feedback, high computational cost, and delayed updates, limiting practical utility in rapidly evolving recommendation catalogs. Inspired by model editing in NLP, which enables training-free knowledge injection into large language models, we explore how to bring this paradigm to generative recommendation. This, however, faces two key challenges: GR lacks the explicit subject-object binding common in natural language, making targeted edits difficult; and GR does not exhibit stable token co-occurrence patterns, making the injection of multi-token item representations unreliable. To address these challenges, we propose GenRecEdit, a model editing framework tailored for generative recommendation. GenRecEdit explicitly models the relationship between the full sequence context and next-token generation, adopts iterative token-level editing to inject multi-token item representations, and introduces a one-to-one trigger mechanism to reduce interference among multiple edits during inference. Extensive experiments on multiple datasets show that GenRecEdit substantially improves recommendation performance on cold-start items while preserving the model's original recommendation quality. Moreover, it achieves these gains using only about 9.5% of the training time required for retraining, enabling more efficient and frequent model updates.

翻译：生成式推荐（GR）在端到端的生成范式下展现出强大的序列推荐潜力。然而，现有的GR模型存在严重的冷启动崩溃问题：其对冷启动物品的推荐准确率可能降至接近零。现有解决方案通常依赖于使用冷启动交互数据进行重新训练，但这种方法受到反馈稀疏、计算成本高昂以及更新延迟的制约，限制了其在快速演进的推荐目录中的实际效用。受自然语言处理中模型编辑技术的启发——该技术能够实现无需训练即可向大语言模型注入知识——我们探索如何将这一范式引入生成式推荐领域。然而，这面临两个关键挑战：GR缺乏自然语言中常见的主客体明确绑定关系，使得针对性编辑变得困难；同时，GR不具备稳定的词元共现模式，导致多词元物品表征的注入不可靠。为应对这些挑战，我们提出了GenRecEdit，一个专为生成式推荐设计的模型编辑框架。GenRecEdit显式建模完整序列上下文与下一个词元生成之间的关系，采用迭代的词元级编辑来注入多词元物品表征，并引入一对一触发机制以减少推理过程中多个编辑之间的相互干扰。在多个数据集上的大量实验表明，GenRecEdit显著提升了模型对冷启动物品的推荐性能，同时保持了模型原有的推荐质量。此外，它仅需约9.5%的重新训练时间即可实现这些性能提升，从而支持更高效、更频繁的模型更新。