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

• URL: http://arxiv.org/abs/2608.25428v1
• Date: Wed, 26 Aug 2026 06:35:26 GMT
• Title: DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models
• Abstract summary: Masked Diffusion Model (MDM) framework for global correction uses an imperfect solution draft from an upstream solver as auxiliary context.<n>DCGC combines task-specificSupervised Fine-Tuning (SFT) with a novel inference-time mechanism called Dynamic Dual-CFG.
• Score: 5.2113270099125915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 relative confidence gap. Across math, code, and knowledge reasoning benchmarks, DCGC outperforms standard sampling and simpler CFG variants, with additional results suggesting transfer to different diffusion backbones. In test-time setting where ground-truth failure labels are unavailable, DCGC improves full test set accuracy by correcting low-consensus upstream outputs, highlighting its utility as a verifier-free global correction module for difficult reasoning instances.

Related papers

• Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion [0.0]
  Two-pass CFG execution pattern imposes a latency overhead that parameter-count and bit-operation metrics conceal entirely.<n>Guidance-Aware Mixed Precision (GAMP) is proposed, which calibrates directly on the guided prediction.
  arXiv  Detail & Related papers  (2026-07-09T08:42:07Z)
• NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO [1.5483078145498086]
  NormWorlds-CF is a solver-verified environment for counterfactual normative reasoning in rule worlds.<n>Its deterministic solver produces final answers, proof and falsification certificates, argument statuses, support sets, and paired-world change labels.
  arXiv  Detail & Related papers  (2026-07-04T17:11:21Z)
• LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition [55.572260012037084]
  We introduce LC-ERD (Logic-Consistent Endogenous Reward Decomposition), a framework framing self-alignment as latent structure mining.<n>We derive a Variational Logic Potential by aggregating consensus from the model's Latent Logic Expertise.<n>Experiments show LC-ERD delivers a robust self-evolution path, uncovering trade-offs between logic consistency and accuracy.
  arXiv  Detail & Related papers  (2026-05-19T07:27:50Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• Manifold-Optimal Guidance: A Unified Riemannian Control View of Diffusion Guidance [21.903550549566575]
  We present a framework that reformulates guidance as a local optimal control problem.<n>MOG yields a closed-form, geometry-aware update that corrects off-manifold drift without requiring retraining.
  arXiv  Detail & Related papers  (2026-03-12T03:51:32Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• Joint Source-Channel-Generation Coding: From Distortion-oriented Reconstruction to Semantic-consistent Generation [58.67925548779465]
  We propose Joint Source-Channel-Generation Coding (JSCGC), a novel paradigm that shifts the focus from perceptual reconstruction to probabilistic generation.<n>JSCGC improves substantially semantic quality and semantic fidelity, significantly outperforming conventional distortion-oriented J SCC methods.
  arXiv  Detail & Related papers  (2026-01-19T08:12:47Z)
• DiffRegCD: Integrated Registration and Change Detection with Diffusion Features [74.3102451211493]
  We present DiffRegCD, an integrated framework that unifies dense registration and change detection in a single model.<n>Experiments on aerial (LEVIR-CD, DSIFN-CD, WHU-CD, SYSU-CD) and ground level (VL-CMU-CD) datasets show that DiffRegCD consistently surpasses recent baselines.
  arXiv  Detail & Related papers  (2025-11-11T07:32:19Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• ASCoT: An Adaptive Self-Correction Chain-of-Thought Method for Late-Stage Fragility in LLMs [21.409155842171497]
  Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs)<n>Errors introduced in the later stages of a CoT chain are significantly more likely to corrupt the final answer than identical errors made at the beginning.<n>We introduce the Adaptive Self-Correction Chain-of-Thought (ASCoT) method to address this specific vulnerability.
  arXiv  Detail & Related papers  (2025-08-07T11:26:40Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.