PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization

arXiv:2603.26535 · cs.AI · Submitted 2026-03-27 · Read on arXiv

cs.AI

Submitted: 2026-03-27

Updated: 2026-08-28

Code: https://github.com/project-numina/aimo-progress-prize

Terminology

• GRPO — 41× in this paper · explained in 6 episodes
• Accuracy — 24× in this paper · explained in 1 episode
• Reward Hacking — 21× in this paper · explained in 8 episodes
• Ablation — 16× in this paper · explained in 1 episode
• Benchmark — 16× in this paper · explained in 2 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Verification — 8× in this paper · explained in 2 episodes
• Large Language Model — 4× in this paper
• Outcome Reward Models — 4× in this paper
• Process Reward Models — 4× in this paper
• Group Relative Policy Optimization — 3× in this paper
• Process-Aware Policy Optimization — 3× in this paper
• Reasoning Traces — 3× in this paper · explained in 3 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Group Relative Policy Optimization (GRPO) — 2× in this paper · explained in 5 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Granularity Mismatch — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• Exploring Reasoning Reward Model for Agents
• Measuring Mathematical Problem Solving With the MATH Dataset
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• HybridFlow: A Flexible and Efficient RLHF Framework
• Defining and Characterizing Reward Hacking
• Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
• Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
• Group Sequence Policy Optimization

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