Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification
cs.LG
Submitted: 2026-05-17
Updated: 2026-11-07
Code: https://github.com/yhkalayci/efficient_query
Terminology
Sources
- Verify to Amplify: Improving Reasoning via Learned Chain-of-Thought Verification
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
- Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
- Qwen2.5-Coder Technical Report
- Optimal Stopping vs Best-of-$N$ for Inference Time Optimization
- Process Reward Models That Think
- When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
- Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical Structure
- Qwen2.5 Technical Report
- AdaBoN: Adaptive Best-of-N Alignment
- Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
- BEACON: Bayesian Optimal Stopping for Efficient LLM Sampling
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization
- CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
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