SOURCE-LINKED INTELLIGENCE

Structural Process Supervision for Latent Chain-of-Thought Reasoning

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space embeddings. However, existing methods lack direct process supervision over these latent embeddings, which often leads to representation collapse and uneven information distribution. To address this, we propose Prototype-Mediated Process Supervision (PMPS), which introduces learnable reasoning prototypes as semantic anchors to provide structural process-level supervision for latent reasoning. PMPS projects latent embeddings and expl

Read original source ↗ Open in workspace

recordType

paper

region

Global