CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning

arXiv:2609.36820 · cs.LG, cs.CL · Submitted 2026-09-29 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/HKUST-KnowComp/CorrGRPO

Terminology

• GRPO — 148× in this paper · explained in 6 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• Core — 10× in this paper · explained in 2 episodes
• Agent Security Bench — 7× in this paper
• Generalization — 6× in this paper · explained in 13 episodes
• Aggregation — 4× in this paper · explained in 1 episode
• Group Relative Policy Optimization — 4× in this paper
• Regularization — 3× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Group Relative Policy Optimization (GRPO) — 2× in this paper · explained in 5 episodes
• KL Regularization — 2× in this paper · explained in 2 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Entropy Collapse — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes

Sources

• Program Synthesis with Large Language Models
• Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
• Evaluating Large Language Models Trained on Code
• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
• Safe RLHF: Safe Reinforcement Learning from Human Feedback
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Qwen2.5-Coder Technical Report
• MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
• Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
• MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
• Training language models to follow instructions with human feedback
• ToolRL: Reward is All Tool Learning Needs
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Multi-objective Reinforcement learning from AI Feedback
• LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs
• Qwen2.5 Technical Report

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks