Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification
cs.AI, cs.CL, cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- RewardBench: Evaluating Reward Models for Language Modeling
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
- TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
- ProcessBench: Identifying Process Errors in Mathematical Reasoning
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection