GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization for Sample-Efficient Reinforcement Learning

arXiv:2601.06795 · cs.AI · Submitted 2026-01-11 · Read on arXiv

cs.AI

Submitted: 2026-01-11

Updated: 2026-10-12

Code: https://github.com/huggingface/open-r1

Terminology

• GRPO — 2× in this paper · explained in 6 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Artificial Intelligence — 1× in this paper
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Automated Theorem Proving — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Group Dual-dynamic and Equal-right-advantage Policy Optimization — 1× in this paper
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
• Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
• Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
• DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
• Leanabell-Prover-V2: Verifier-integrated Reasoning for Formal Theorem Proving via Reinforcement Learning
• DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
• Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
• Solving Formal Math Problems by Decomposition and Iterative Reflection
• DeepSeek-V3 Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Proximal Policy Optimization Algorithms
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
• GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models

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
• Agents' Last Exam
• 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