标签
The paper proposes an unsupervised self-evolving agent framework inspired by diffusion models, using self-supervised semantic diffusion to train external skill libraries for LLM agents in specialized domains like creative screenwriting, without requiring weight access or external supervision.
本文从偏差-方差角度对扩散语言模型进行了理论分析，识别了掩码扩散与均匀扩散核之间的权衡。提出了SemDLM+，通过添加全局转移和语义频率惩罚来克服语义盆地问题，在LM1B和OpenWebText基准上实现了有竞争力的生成质量。