mlsanityData to 14 Oct 2026

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

arXiv 2508.09670 ↗First posted 13 Aug 2025cs.AIcited by 14

On the map: LLM reasoning → Reinforcement learning for reasoning

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.

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.

Builds on

24 of 49 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Example29 Apr
  2. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?18 Apr
  3. 2025Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining10 Apr
  4. 2025Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning6 Apr
  5. 2025Understanding R1-Zero-Like Training: A Critical Perspective26 Mar
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning22 Jan
  7. 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning10 Oct

Other references · 17

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2025s1: Simple test-time scalingcited by 1,341
  8. 2024OpenAI o1 System Cardcited by 1,244
  9. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  10. 2025LIMO: Less is More for Reasoningcited by 498
  11. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
  12. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyondcited by 175
5 more
  1. 2025S*: Test Time Scaling for Code Generationcited by 98
  2. 2025Concise Reasoning via Reinforcement Learningcited by 79
  3. 2025Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoningcited by 35
  4. 2025CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuningcited by 8
  5. 2025EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Modelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generationcited by 7
  2. 2026LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Datacited by 0
  3. 2026Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Methodcited by 0
  4. 2026MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreadingcited by 0
  5. 2026The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separationcited by 0
  6. 2026Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignmentcited by 0
  7. 2026Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networkscited by 0
  8. 2026A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspectioncited by 0
  9. 2026Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazingcited by 0
  10. 2026Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Predictioncited by 0
  11. 2026Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spottingcited by 0
  12. 2026IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Viewscited by 0
2 more
  1. 2026Rank-Consistent Set Reasoning for Co-Salient Object Detectioncited by 0
  2. 2026Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
  2. 2026MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models
  3. 2025Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models
  4. 2026GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings
  5. 2025Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation
  6. 2025Can GRPO Help LLMs Transcend Their Pretraining Origin?
  7. 2025λ-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences
  8. 2025Sharpness-Guided Group Relative Policy Optimization via Probability Shaping