paper-with-me

홈 › Papers

Efficient RL Training for Reasoning Models via Length-Aware Optimization

2025-05-18 · Danlong Yuan, Tian Xie, Shaohan Huang, Zhuocheng Gong, Huishuai Zhang, Chong Luo, Furu Wei, Dongyan Zhao

Large reasoning models, such as OpenAI o1 or DeepSeek R1, have demonstrated remarkable performance on reasoning tasks but often incur a long reasoning path with significant memory and time costs. Existing methods primarily aim to shorten reasoning paths by introducing additional training data and stages. In this paper, we propose three critical reward designs integrated directly into the reinforcement learning process of large reasoning models, which reduce the response length without extra training stages. Experiments on four settings show that our method significantly decreases response length while maintaining or even improving performance. Specifically, in a logic reasoning setting, we achieve a 40% reduction in response length averaged by steps alongside a 14% gain in performance. For math problems, we reduce response length averaged by steps by 33% while preserving performance.

📄 PDF Abstract BibTeX arXiv:2505.12284

Code (1)

lblankl/short-rl 공식 구현 pytorch

Tasks

Math

Similar Papers 제목 키워드 기반

LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning

2025-10-01 · Weizhe Chen, Sven Koenig, Bistra Dilkina arxiv

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modif…

Reinforcement Learning

Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation

2025-09-05 · Abdul Waheed, Chancharik Mitra, Laurie Z. Wang, Deva Ramanan 외 arxiv

Chain-of-thought reasoning, while powerful, can produce unnecessarily verbose output for simpler problems. We present a framework for difficulty-aware reasoning that teaches models to dynamically adjust reasoning depth b…

HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization

2025-05-16 · Chengyu Huang, Zhengxin Zhang, Claire Cardie

While scaling the length of responses at test-time has been shown to markedly improve the reasoning abilities and performance of large language models (LLMs), it often results in verbose outputs and increases inference c…

Math

CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs

2026-06-18 · Chengwen Liu, Hao Peng, Jisheng Dang, Hong Peng 외 arxiv

In multimodal video reasoning, reinforcement learning-based methods typically rely on simplistic and inflexible reasoning-length control strategies that fail to adapt to the model's evolving competence. This mismatch may…

Reinforcement LearningMultimodal Reasoning

CLORE: Content-Level Optimization for Reasoning Efficiency

2026-05-21 · Yuyang Wu, Qiyao Xue, Guanxing Lu, Weichen Liu 외 arxiv

Reinforcement learning post-training has improved the reasoning ability of large language models, but often produces unnecessarily long, repetitive, or semantically opaque reasoning traces. Existing efficient reasoning m…

Reinforcement LearningMathematical Reasoning