让大模型生成像生命一样自我调节，避免重复坍缩。
Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models
- 用动态反馈控制语义吸引与语法排斥的平衡。
- 发现可稳定存在的‘稳态孤子’结构，抵抗重复固化。
- 适合研究生成模型稳定性与创造性机制的人看。
我们提出语义伦尼亚（Semantic Lenia），将大语言模型推理从静态优化问题转变为连续闭合回路的动力系统。通过构建非线性稳态反馈机制，动态平衡语义吸引与语法排斥，成功催生出‘稳态孤子’——一种能主动抵抗重复结晶的亚稳态语义结构。全面参数扫描揭示了关键的‘宜居脊线’，在此区域施加的引导力与模型内在语法惯性达到平衡。该方法使生成轨迹长期维持在数值敏感的临界状态，触发深刻的归纳跃迁而无结构崩溃，并发现不同模型规模下语法惯性具有容量依赖的标度规律。
原文摘要 · Abstract (English)
We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference from a static optimization problem into a continuous, closed-loop dynamical system. By establishing a non-linear homeostatic feedback loop to dynamically balance semantic attraction and syntactic repulsion, we demonstrate the emergence of ``Homeostatic Solitons''-metastable semantic structures that actively resist repetitive crystallization. Our exhaustive parameter sweeps map a critical ``Habitable Ridge'' where applied steering forces balance the model's intrinsic syntactic inertia. This approach successfully maintains generative trajectories in a numerically sensitive critical regime, triggering profound abductive leaps without structural collapse, and reveals a capacity-dependent scaling trend in the syntactic inertia across different model sizes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。