Current autoregressive language models couple high-level reasoning and low-level token generation into a single sequential process, making the reasoning trajectory vulnerable to compounding expression errors. We propose JEPA-Reasoner, a novel architectural paradigm that decouples these tasks using a Joint-Embedding Predictive Architecture (JEPA) for pure latent-space reasoning and a separate Talker module for linguistic reconstruction. By isolating the reasoning engine from the discrete token-sampling process, our architecture enables: (1) Error Containment, where token-level failures cannot propagate into the latent reasoning chain; (2) Continuous Guidance, providing the generator with access to the entire lossless reasoning trajectory; and (3) Representation of Uncertainty, allowing the model to maintain multiple hypotheses via mixed latent vectors. Controlled experiments on synthetic and natural language tasks demonstrate that this decoupling enables a 0.9B model to achieve a 149.5\% improvement in 8-shot GSM8K accuracy over a coupled Transformer baseline trained on identical data. This work shifts the focus from scaling coupled models to investigating decoupled architectures as a more robust foundation for complex reasoning.

翻译：当前的自回归语言模型将高层推理与低层词元生成耦合为单一的顺序过程，使得推理轨迹容易受到复合表达误差的影响。我们提出JEPA-Reasoner，一种新颖的架构范式，它利用联合嵌入预测架构进行纯潜在空间推理，并采用独立的Talker模块进行语言重建，从而将这两项任务解耦。通过将推理引擎与离散词元采样过程隔离，我们的架构实现了：（1）错误遏制，词元级故障无法传播到潜在推理链中；（2）连续引导，为生成器提供访问完整无损推理轨迹的能力；（3）不确定性表示，允许模型通过混合潜在向量维持多个假设。在合成任务和自然语言任务上的受控实验表明，这种解耦使得一个0.9B参数的模型在8-shot GSM8K准确率上，相比在相同数据上训练的耦合Transformer基线实现了149.5%的提升。这项工作将研究重点从扩展耦合模型转向探索解耦架构，为复杂推理提供了更鲁棒的基础。