Scale Down to Speed Up: Dynamic Data Selection for Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to Reinforcement Learning (RL) rely on massive static datasets, leading to computational inefficiency and redundant gradient updates. |
| Approach: | They propose a data-centric RL framework that dynamically selects the most informative training samples to optimize RL for mathematical reasoning. |
| Outcome: | The proposed framework achieves comparable performance to full-data training methods while requiring only 1.5K samples instead of 220K, reducing training time from 13 days to just 4 hours on 8A800 GPUs. |
Similar Papers
FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Improving training efficiency remains a challenge in large-scale Reinforcement Learning (RL). |
| Approach: | They propose a curriculum RL framework with stage-wise context scaling to improve RL training efficiency. |
| Outcome: | The proposed framework outperforms state-of-the-art reasoning models on five benchmarks and achieves 49.6% accuracy on AIME 2024. |
SCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) is a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. |
| Approach: | They propose a framework that sustains effective learning signals through adaptive environment design that transforms real-world programming problems into verifiable reasoning environments with controllable difficulty and unbounded instance generation. |
| Outcome: | The proposed framework outperforms baselines across diverse reasoning benchmarks and exhibits more stable, long-horizon training dynamics. |
Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches allocate an equal number of rollouts to all questions during the RL process, which is inefficient. |
| Approach: | They propose a mechanism for dynamically allocating rollout budgets based on the difficulty of the problems, enabling more efficient RL training. |
| Outcome: | The proposed model improves response precision while preserving exploratory ability to uncover potential correct pathways. |
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)
Copied to clipboard
Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo
| Challenge: | Existing research on reinforcement learning for LLMs under data scarcity has not been unified. |
| Approach: | They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric. |
| Outcome: | The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area. |
From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has recently advanced the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose a method that incorporates partial solution prefixes from expert demonstrations to guide the policy. |
| Outcome: | The proposed methods outperform strong baselines, yielding faster convergence and a higher performance ceiling. |
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis (2026.findings-acl)
Copied to clipboard
| Challenge: | SynthRL synthesizes over 3.3K additional verifiable, challenging questions from approximately 8K seed samples. |
| Approach: | They propose a scalable and guaranteed pipeline for automatic data scaling in reasoning-oriented RL training. |
| Outcome: | The proposed pipeline synthesizes over 3.3K additional verifiable, challenging questions from approximately 8K seed samples. |
Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that EasyRL consistently outperforms state-of-the-art baselines due to the substantial annotation cost and issues such as model collapse or reward hacking. |
| Approach: | They propose a supervised RL approach with a divide-and-conquer strategy that simulates the human cognitive acquisition curve using easy labeled data. |
| Outcome: | The proposed approach outperforms state-of-the-art models on mathematical and scientific benchmarks using only 10% of easy labeled data. |
SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training pipelines sample training examples uniformly across steps or epochs, ignoring differences in difficulty, redundancy, and learning value, which slows learning and wastes computation. |
| Approach: | They propose a self-paced learning framework that enables efficient learning based on the capability of the model being trained through optimizing which data to use and when. |
| Outcome: | The proposed framework achieves comparable or better accuracy than state-of-the-art baselines while using up to (100 times) fewer samples. |
Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite advances in reinforcement learning, data collection and fine-tuning remain costly and hard to scale. |
| Approach: | They propose a video-adaptive test-time scaling strategy that combines RL with a supervised fine-tuning strategy to improve video reasoning capability. |
| Outcome: | The proposed method surpasses existing models by 2.4% in accuracy using only 3.6% training samples. |
RAISE: Reinforced Adaptive Instruction Selection For Large Language Models (2025.findings-emnlp)
Copied to clipboard
Qingsong Lv, Yangning Li, Zihua Lan, Zishan Xu, Jiwei Tang, Tingwei Lu, Yinghui Li, Wenhao Jiang, Hong-Gee Kim, Hai-Tao Zheng, Philip S. Yu
| Challenge: | Existing selection methods rely on static, heuristic quality scores and are executed only once before training. |
| Approach: | They propose a dynamic selection framework that integrates selection into every training step. |
| Outcome: | The proposed framework integrates selection into every training step. |