# MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement

arXiv: https://arxiv.org/abs/2508.09670 · HTML: https://mlsanity.com/paper/2508.09670/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond](https://mlsanity.com/paper/2503.10460/) (2025)
- [Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining](https://mlsanity.com/paper/2504.07912/) (2025)
- [S*: Test Time Scaling for Code Generation](https://mlsanity.com/paper/2502.14382/) (2025)
- [Concise Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2504.05185/) (2025)
- [Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning](https://mlsanity.com/paper/2505.15154/) (2025)
- [Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning](https://mlsanity.com/paper/2504.04524/) (2025)
- [CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.00568/) (2025)
- [EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models](https://mlsanity.com/paper/2503.04058/) (2025)

## Built on by (most cited first, 14 of 14)

- [Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation](https://mlsanity.com/paper/2602.03045/) (2026)
- [LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data](https://mlsanity.com/paper/2601.09118/) (2026)
- [Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method](https://mlsanity.com/paper/2601.09238/) (2026)
- [MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading](https://mlsanity.com/paper/2601.20881/) (2026)
- [The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separation](https://mlsanity.com/paper/2602.13361/) (2026)
- [Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment](https://mlsanity.com/paper/2602.15903/) (2026)
- [Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks](https://mlsanity.com/paper/2603.00118/) (2026)
- [A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection](https://mlsanity.com/paper/2603.13429/) (2026)
- [Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing](https://mlsanity.com/paper/2603.29507/) (2026)
- [Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction](https://mlsanity.com/paper/2604.03339/) (2026)
- [Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting](https://mlsanity.com/paper/2605.18173/) (2026)
- [IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views](https://mlsanity.com/paper/2608.24020/) (2026)
- [Rank-Consistent Set Reasoning for Co-Salient Object Detection](https://mlsanity.com/paper/2609.13706/) (2026)
- [Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detection](https://mlsanity.com/paper/2609.14383/) (2026)

## Abstract (arXiv)

Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where zero rewards from consistently incorrect candidate answers provide no learning signal, particularly in challenging tasks. To address this, we propose Multi-Expert Mutual Learning GRPO (MEML-GRPO), an innovative framework that utilizes diverse expert prompts as system prompts to generate a broader range of responses, substantially increasing the likelihood of identifying correct solutions. Additionally, we introduce an inter-expert mutual learning mechanism that facilitates knowledge sharing and transfer among experts, further boosting the model's performance through RLVR. Extensive experiments across multiple reasoning benchmarks show that MEML-GRPO delivers significant improvements, achieving an average performance gain of 4.89% with Qwen and 11.33% with Llama, effectively overcoming the core limitations of traditional RLVR methods.