paper-with-me

Papers

Evaluating Parameter Efficient Methods for RLVR

2025-12-29 · Qingyu Yin, Yulun Wu, Zhennan Shen, Sunbowen Li, Zhilin Wang, Yanshu Li, Chak Tou Leong, Jiale Kang, Jinjin Gu arxiv

We systematically evaluate Parameter-Efficient Fine-Tuning (PEFT) methods under the paradigm of Reinforcement Learning with Verifiable Rewards (RLVR). RLVR incentivizes language models to enhance their reasoning capabilities through verifiable feedback; however, while methods like LoRA are commonly used, the optimal PEFT architecture for RLVR remains unidentified. In this work, we conduct the first comprehensive evaluation of over 12 PEFT methodologies across the DeepSeek-R1-Distill families on mathematical reasoning benchmarks. Our empirical results challenge the default adoption of standard LoRA with three main findings. First, we demonstrate that structural variants, such as DoRA, AdaLoRA, and MiSS, consistently outperform LoRA. Second, we uncover a spectral collapse phenomenon in SVD-informed initialization strategies (\textit{e.g.,} PiSSA, MiLoRA), attributing their failure to a fundamental misalignment between principal-component updates and RL optimization. Furthermore, our ablations reveal that extreme parameter reduction (\textit{e.g.,} VeRA, Rank-1) severely bottlenecks reasoning capacity. We further conduct ablation studies and scaling experiments to validate our findings. This work provides a definitive guide for advocating for more exploration for parameter-efficient RL methods.

📄 PDF Abstract BibTeX arXiv:2512.23165

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningReinforcement LearningMathematical Reasoning

Similar Papers 제목 키워드 기반

Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging

2026-06-16 · Chenrui Wu, Zexi Li, Jiajun Bu, Jiangchuan Liu 외 arxiv

Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful post-training paradigm that surpasses Supervised Fine-Tuning (SFT) in eliciting reasoning intelligence and resisting catastrophic forgetting.…

Reinforcement Learning

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR

2026-01-14 · Jiaying Zhang, Lei Shi, Jiguo Li, Jun Xu 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) is a key paradigm for improving large-scale reasoning models. Unlike supervised fine-tuning (SFT), RLVR exhibits distinct optimization dynamics and is sensitive to th…

Reinforcement Learning

The Path Not Taken: RLVR Provably Learns Off the Principals

2025-11-11 · Hanqing Zhu, Zhenyu Zhang, Hanxian Huang, DiJia Su 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) reliably improves the reasoning performance of large language models, yet it appears to modify only a small fraction of parameters. We revisit this paradox and show t…

parameter-efficient fine-tuningReinforcement Learning

Beyond Accuracy: Evaluating Visual Grounding In Multimodal Medical Reasoning

2026-03-03 · Anas Zafar, Leema Krishna Murali, Ashish Vashist arxiv

Recent work shows that text-only reinforcement learning with verifiable rewards (RLVR) can match or outperform image-text RLVR on multimodal medical VQA benchmarks, suggesting current evaluation protocols may fail to mea…

Reinforcement LearningVisual ReasoningVisual Grounding

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration

2026-04-13 · Zhipeng Chen, Tao Qian, Wayne Xin Zhao, Ji-Rong Wen arxiv

Recently, scaling reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs) has emerged as an effective training paradigm for significantly improving model capabilities, which requires guidin…

Reinforcement Learning