Language-Reasoning JEPA: Searching Imagined Futures over Language

A language model reasons by generating text about the future with the same likelihood readout that chooses its actions, and it has no separate mechanism for imagining what an action would do. Action-conditioned joint-embedding predictive architectures (JEPAs) supply such a mechanism in robotic control, and we study whether the same construction supports reasoning over language. We read a sentence as a partial observation of a controlled process and a derivation step as an intervention, whose observed consequence is the supervision a JEPA is trained to predict. Transition prediction determines the dynamics of the latent space but leaves its metric free, so we add a goal-conditioned energy head that we train only by ranking outcomes the environment has executed, and we plan by model-predictive control over imagined latent trajectories. We call the model Language-Reasoning JEPA (LR-JEPA) and evaluate it in two synthetic environments rendered entirely in language, where every policy selects its next step from the same menu of admissible actions and we measure overshoot, the number of executed actions relative to the shortest solution. On chain-structured deduction, language models trained on the same trajectories are optimal inside the trained lengths and reach overshoot $1.69$ to $1.91$ beyond them, where a random policy reaches $2.01$. The same ranking head on the frozen language model reaches $1.03$ at search depth one and falls to the random level by depth four, because a language model cannot roll its state forward and appending the true consequences of imagined steps to its context does not restore search reliably, while LR-JEPA improves from $1.31$ to $1.09$ over those depths. On dependency graphs the search degrades with depth, which we trace to the drift of imagined trajectories.