Qwen-3-4B

The 'Qwen-3-4B' is a dataset/benchmark used to evaluate the performance of reinforcement learning (RL) systems in training large language models (LLMs) by assessing their convergence speed and final reward in a distributed cluster environment.

Papers using Qwen-3-4B (3)

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning2026Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States2026Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms2025