Inference-Time Amplification of Weak Reasoning Models

arXiv:2605.14163 · cs.AI · Submitted 2026-05-13 · Read on arXiv

cs.AI

Submitted: 2026-05-13

Updated: 2026-10-04

Terminology

• Verifier — 2× in this paper · explained in 2 episodes

Sources

• Learning to Give Checkable Answers with Prover-Verifier Games
• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• Evaluating Large Language Models Trained on Code
• Universal Self-Consistency for Large Language Model Generation
• Supervising strong learners by amplifying weak experts
• AI safety via debate
• FUSE: Ensembling Verifiers with Zero Labeled Data
• A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

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