Reasoning as Energy Minimization over Structured Latent Trajectories

ArXi:2603.28248v1 Announce Type: new Single-shot neural decoders commit to answers without iterative refinement, while chain-of-thought methods We identify a critical failure mode: on CNF logic satisfaction, latent planning reduces accuracy from $\approx 95\%$ to $\approx 56\%$. This degradation arises from a distribution mismatch, where the decoder is trained on encoder outputs $h_x$ but evaluated on planner outputs $z_T$ that drift into unseen latent regions. We analyze this behavior through per-step decoding, latent drift tracking, and gradient decomposition.