paper-with-me

Papers

How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study

2025-04-01 · Yunjie Ji, Sitong Zhao, Xiaoyu Tian, Haotian Wang, Shuaiting Chen, Yiping Peng, Han Zhao, Xiangang Li

Enhancing the reasoning capabilities of Large Language Models (LLMs) with efficiency and scalability remains a fundamental challenge in artificial intelligence research. This paper presents a rigorous experimental investigation into how difficulty-aware staged reinforcement learning (RL) strategies can substantially improve LLM reasoning performance. Through systematic analysis, we demonstrate that strategically selecting training data according to well-defined difficulty levels markedly enhances RL optimization. Moreover, we introduce a staged training methodology, progressively exposing models to increasingly challenging tasks, further amplifying reasoning capabilities. Our findings reveal significant cross-domain benefits when simultaneously training models on mathematical reasoning and code generation tasks. Notably, our proposed approach enables a 1.5B parameter model to achieve an accuracy of 42.3\% on the AIME-2024 benchmark, 89.5\% on the MATH-500 benchmark. These results underscore the efficacy of our method in advancing the reasoning proficiency of LLMs. We will open-source our datasets on GitHub and Hugging Face.

📄 PDF Abstract BibTeX arXiv:2504.00829

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationMathMathematical ReasoningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention

2025-08-03 · Xinhan Di, JoyJiaoW arxiv

Reinforcement learning scaling enhances the reasoning capabilities of large language models, with reinforcement learning serving as the key technique to draw out complex reasoning. However, key technical details of state…

Reinforcement Learning

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

2025-06-04 · Shuang Chen, Yue Guo, Zhaochen Su, Yafu Li 외

Inspired by the remarkable reasoning capabilities of Deepseek-R1 in complex textual tasks, many works attempt to incentivize similar capabilities in Multimodal Large Language Models (MLLMs) by directly applying reinforce…

Multimodal ReasoningReinforcement Learning (RL)

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training

2025-05-25 · Weize Chen, Jiarui Yuan, Tailin Jin, Ning Ding 외

Recent large language models (LLMs) exhibit impressive reasoning but often over-think, generating excessively long responses that hinder efficiency. We introduce DIET ( DIfficulty-AwarE Training), a framework that system…

Reinforcement Learning (RL)Token Reduction

GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning

2025-07-14 · Ziru Liu, Cheng Gong, Xinyu Fu, Yaofang Liu 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tas…

Reinforcement Learning

EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO

2025-07-29 · Wei Guan, Jun Lan, Jian Cao, Hao Tan 외 arxiv

Industrial anomaly detection (IAD) plays a crucial role in maintaining the safety and reliability of manufacturing systems. While multimodal large language models (MLLMs) show strong vision-language reasoning abilities, …

Anomaly Detection