Fed-GRPO: Reward-Signal-Driven Federated Group Relative Policy Optimization
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-08
Code: https://github.com/HKUHealthAI/Fed-GRPO
Terminology
Sources
- Program Synthesis with Large Language Models
- FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Exploring Federated Pruning for Large Language Models
- GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
- Overcoming the Communication-Performance Tradeoff in LLM Pretraining
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards
- Qwen3 Technical Report
- Qwen2.5 Technical Report
- Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
- FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-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