Verifier-Guided Self-Consistency: Test-Time Reasoning with Imperfect Generators and Verifiers
cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/cant-access-rediska0123/vgsc
Terminology
Sources
- Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs
- More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
- The Llama 3 Herd of Models
- Gemma 3 Technical Report
- Scaling Laws for Neural Language Models
- Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees
- ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
- Value-Guided Search for Efficient Chain-of-Thought Reasoning
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis