Standard autoregressive language models collapse uncertainty at every generation step by committing to discrete tokens through immediate sampling. This premature discretization underlies well-known failure modes, including degenerate repetition loops in greedy decoding and a heavy reliance on heuristic sampling strategies. We introduce \textbf{Token Maturation}, a continuous autoregressive framework in which tokens evolve as vector-valued trajectories prior to discretization. Rather than sampling from a categorical distribution at each step, the model resolves uncertainty through a deterministic dynamical process in embedding space, deferring discrete commitment until the representation has geometrically stabilized. We show that this formulation mitigates degeneration \emph{intrinsically}: Token Maturation generates coherent and diverse text under fully deterministic decoding (argmax), without repetition penalties, temperature scaling, or stochastic sampling. Moreover, we identify a novel convergence behavior in which token representations stabilize spatially while predictive entropy remains high, challenging the common assumption that commitment requires probability concentration. We propose continuous token dynamics with delayed commitment as an alternative formulation of autoregressive generation that exposes structural regularities obscured by immediate discretization.

翻译：标准的自回归语言模型通过即时采样对离散词元做出承诺，从而在每一生成步骤中坍缩了不确定性。这种过早的离散化是导致已知失效模式的根本原因，包括贪婪解码中的退化重复循环以及对启发式采样策略的严重依赖。我们提出\textbf{词元成熟}，一种连续自回归框架，其中词元在离散化之前作为向量值轨迹演化。模型并非在每一步从分类分布中采样，而是通过在嵌入空间中的确定性动力学过程来解决不确定性，直到表示在几何上稳定后才做出离散承诺。我们证明，该公式能够\textit{本质地}缓解退化：词元成熟在完全确定性解码（argmax）下生成连贯且多样的文本，无需重复惩罚、温度缩放或随机采样。此外，我们发现了一种新的收敛行为，即词元表示在空间上稳定，而预测熵仍保持高位，这挑战了“做出承诺需要概率集中”这一常见假设。我们提出具有延迟承诺的连续词元动力学，作为自回归生成的一种替代公式，它揭示了被即时离散化所掩盖的结构规律。