SOURCE-LINKED INTELLIGENCE

DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Correcting flawed reasoning traces remains a significant challenge for Large Language Models (LLMs), whose autoregressive generation can propagate early mistakes into subsequent reasoning. We introduce DCGC, a Masked Diffusion Model (MDM) framework for global correction that uses an imperfect solution draft from an upstream solver as auxiliary context. DCGC combines task-specific Supervised Fine-Tuning (SFT) with a novel inference-time mechanism called Dynamic Dual-CFG. This mechanism separates problem-only and joint problem-draft branches and scales the draft-conditioned residual using a rela

Read original source ↗ Open in workspace

recordType

paper

region

Global