Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces

arXiv:2610.18606 · cs.AI, cs.CL · Submitted 2026-10-13 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 19 pages, 5 figures, 4 tables. Under review

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 1× in this paper
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• ARGORA: Orchestrated Argumentation for Causally Grounded LLM Reasoning and Decision Making
• Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation
• Qwen2.5 Technical Report
• Qwen3 Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems