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

• URL: http://arxiv.org/abs/2504.00829v1
• Date: Tue, 01 Apr 2025 14:18:38 GMT
• Title: How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study
• Authors: Yunjie Ji, Sitong Zhao, Xiaoyu Tian, Haotian Wang, Shuaiting Chen, Yiping Peng, Han Zhao, Xiangang Li,
• Abstract summary: This paper presents a rigorous experimental investigation into how difficulty-aware staged reinforcement learning strategies can substantially improve reasoning performance.<n>We show that strategically selecting training data according to well-defined difficulty levels markedly enhances RL optimization.<n>We will open-source our datasets on GitHub and Hugging Face.
• Score: 16.441081996257576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Demystifying Reinforcement Learning in Agentic Reasoning [90.3737088727791]
  We conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning.<n>We highlight our key insights: (i) replacing stitched synthetic trajectories with real end-to-end tool-use trajectories yields a far stronger SFT.<n> Exploration-friendly techniques are crucial for agentic RL, such as clip higher, overlong reward shaping, and maintaining adequate policy entropy could improve the training efficiency.
  arXiv  Detail & Related papers  (2025-10-13T17:57:15Z)
• MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization [103.74675519953898]
  Long-chain reflective reasoning is a prerequisite for solving complex real-world problems.<n>We build a benchmark consisting 1,260 samples of 42 challenging synthetic tasks.<n>We generate post-training data and explore learning paradigms for exploiting such data.
  arXiv  Detail & Related papers  (2025-10-09T17:53:58Z)
• The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback [51.144727949988436]
  Reinforcement learning (RL) has demonstrated potential to enhance the reasoning capabilities of large language models (LLMs)<n>In this work, we explore improving LLMs through RL with minimal data.<n>To minimize data dependency, we introduce two novel mechanisms grounded in self-awareness.
  arXiv  Detail & Related papers  (2025-10-03T06:32:10Z)
• Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning [42.80470927369973]
  We study how model scale, data volume, and computational budget interact to shape performance.<n>We find that larger models trained for fewer steps consistently outperform smaller models trained for more steps.<n>In data-constrained regimes, repeated reuse of high-quality data proves highly effective.
  arXiv  Detail & Related papers  (2025-09-29T17:10:35Z)
• Pushing LLMs to Their Logical Reasoning Bound: The Role of Data Reasoning Intensity [59.27594125465172]
  We introduce Data Reasoning Intensity (DRI), a novel metric that quantifies the latent logical reasoning complexity of samples.<n>We then introduce a re-cognizing optimization strategy that systematically enhances the logical reasoning intensity of training data.
  arXiv  Detail & Related papers  (2025-09-29T14:20:04Z)
• Omni-Thinker: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards [50.21528417884747]
  We introduce Omni-Thinker, a unified reinforcement learning framework that enhances large language models (LLMs) performance across diverse tasks.<n>Our approach enables consistent optimization across task types and scales RL-based training to subjective domains.<n> Experimental results across four domains reveal that curriculum learning improves performance by 5.2% over joint training and 9.1% over model merging.
  arXiv  Detail & Related papers  (2025-07-20T01:50:16Z)
• GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning [15.43938821214447]
  Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs)<n>This paper introduces Guided Hybrid Policy Optimization (GHPO), a novel difficulty-aware reinforcement learning framework.<n>GHPO dynamically calibrates task difficulty by employing adaptive prompt refinement to provide targeted guidance.
  arXiv  Detail & Related papers  (2025-07-14T08:10:00Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [82.43575191712726]
  We introduce a fine-grained analytic framework to dissect the impact ofReinforcement learning on reasoning.<n>Our framework specifically investigates key elements that have been hypothesized to benefit from RL training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs) We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization. OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.<n>Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.<n>Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling [69.57918638435491]
  Test-Time Scaling is an important method for improving the performance of Large Language Models. This paper focuses on two core questions: What is the optimal approach to scale test-time computation across different policy models, PRMs, and problem difficulty levels? We show that with our compute-optimal TTS strategy, extremely small policy models can outperform larger models.
  arXiv  Detail & Related papers  (2025-02-10T17:30:23Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.<n>Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.<n>We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs [22.177654792824896]
  We focus on small-sized language models (3B to 7B parameters) for their cost-efficiency and accessibility. We explore various training configurations and strategies across four open-source pre-trained models. Key insights from our work include: (i) larger batch sizes paired with lower learning rates lead to improved model performance on benchmarks such as MMLU, MTBench, and Open LLM Leaderboard; (ii) early-stage training dynamics, such as lower gradient norms and higher loss values, are strong indicators of better final model performance; (iv) we observed no significant difference in performance between phased and stacked training strategies, but
  arXiv  Detail & Related papers  (2024-12-17T21:16:59Z)
• EVOLvE: Evaluating and Optimizing LLMs For Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty. We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications. Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• The Role of Deductive and Inductive Reasoning in Large Language Models [37.430396755248104]
  We propose the Deductive and InDuctive(DID) method to enhance Large Language Models (LLMs) reasoning.<n>DID implements a dual-metric complexity evaluation system that combines Littlestone dimension and information entropy.<n>Our results demonstrate significant improvements in reasoning quality and solution accuracy.
  arXiv  Detail & Related papers  (2024-10-03T18:30:47Z)
• Achieving Peak Performance for Large Language Models: A Systematic Review [0.0]
  Large language models (LLMs) have achieved remarkable success in natural language processing (NLP) As models grow into the trillion- parameter range, computational and memory costs increase significantly. This makes it difficult for many researchers to access the resources needed to train or apply these models.
  arXiv  Detail & Related papers  (2024-09-07T13:57:41Z)
• Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs [12.48241058167222]
  Large Language Models (LLMs) have demonstrated remarkable efficiency in tackling various tasks based on human instructions. But studies reveal that they often struggle with tasks requiring reasoning, such as math or physics limitation. This raises questions about whether LLMs truly comprehend embedded knowledge or merely learn to replicate the token distribution without a true understanding of the content. We propose Decon Causal Adaptation (DCA), a novel parameter-efficient fine-tuning (PEFT) method to enhance the model's reasoning capabilities.
  arXiv  Detail & Related papers  (2024-09-04T13:17:09Z)
• Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks [90.11273439036455]
  Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks. We propose Knowledge-Augmented Reasoning Distillation (KARD), a novel method that fine-tunes small LMs to generate rationales from LLMs with augmented knowledge retrieved from an external knowledge base. We empirically show that KARD significantly improves the performance of small T5 and GPT models on the challenging knowledge-intensive reasoning datasets.
  arXiv  Detail & Related papers  (2023-05-28T13:00:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.