S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models

For correct answers within a serial group, rewards gradually decrease based on the exit positions along the reasoning path from front to back. This design encourages the model to produce more accurate and concise thoughts, while also incentivizing early thinking termination when appropriate. Empirical evaluations demonstrate that S-GRPO is compatible with state-of-the-art reasoning models, including Qwen3 and Deepseek-distill. Across diverse benchmarks such as GSM8K, AIME 2024, AMC 2023, MATH-500, and GPQA Diamond, SGRPO achieves a substantial reduction in sequence length (40.4% 61.1%) while simultaneously improving accuracy (absolute 0.72% 3.92%).