Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning

📝 Original Info

• Title: Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
• ArXiv ID: 2510.19807
• Date: 2025-10-22
• Authors: ** 논문에 명시된 저자 정보가 제공되지 않았습니다. (저자명 및 소속을 확인할 수 있는 경우 추가해 주세요.) **

📝 Abstract

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by the ''learning cliff'' phenomenon: when faced with problems far beyond their current capabilities, models consistently fail, yielding a persistent zero-reward signal. In policy optimization algorithms like GRPO, this collapses the advantage calculation to zero, rendering these difficult problems invisible to the learning gradient and stalling progress. To overcome this, we introduce Scaf-GRPO (Scaffolded Group Relative Policy Optimization), a progressive training framework that strategically provides minimal guidance only when a model's independent learning has plateaued. The framework first diagnoses learning stagnation and then intervenes by injecting tiered in-prompt hints, ranging from abstract concepts to concrete steps, enabling the model to construct a valid solution by itself. Extensive experiments on challenging mathematics benchmarks demonstrate Scaf-GRPO's effectiveness, boosting the pass@1 score of the Qwen2.5-Math-7B model on the AIME24 benchmark by a relative 44.3% over a vanilla GRPO baseline. This result demonstrates our framework provides a robust and effective methodology for unlocking a model's ability to solve problems previously beyond its reach, a critical step towards extending the frontier of autonomous reasoning in LLM.

💡 Deep Analysis

📄 Full Content

Reference