Image de couverture de livre

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yue, Yang, Chen, Zhiqi, Lu, Rui, Zhao, Andrew, Wang, Zhaokai, Song, Shiji, Huang, Gao
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
par: Wang, Shenzhi, et autres
Publié: (2025)

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
par: Huang, Wei, et autres
Publié: (2025)

Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
par: Huang, Shulin, et autres
Publié: (2025)

Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
par: Wang, Haozhe, et autres
Publié: (2025)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
par: Wen, Xumeng, et autres
Publié: (2025)

ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning
par: Li, Yifan, et autres
Publié: (2025)

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
par: Wang, Yulin, et autres
Publié: (2024)

BabyVision: Visual Reasoning Beyond Language
par: Chen, Liang, et autres
Publié: (2026)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
par: Wang, Shenzhi, et autres
Publié: (2026)

Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
par: Lu, Meng, et autres
Publié: (2025)

Cross-Modal Adapter for Vision-Language Retrieval
par: Jiang, Haojun, et autres
Publié: (2022)

Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?
par: Geigle, Gregor, et autres
Publié: (2024)

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
par: Yang, Wanli, et autres
Publié: (2026)

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
par: Yue, Yang, et autres
Publié: (2025)

EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance
par: Yue, Yang, et autres
Publié: (2025)

AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?
par: Gong, Kaixiong, et autres
Publié: (2024)

DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry
par: Cai, Zhenyang, et autres
Publié: (2025)

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
par: Wei, Lai, et autres
Publié: (2025)

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
par: Zhong, Yufeng, et autres
Publié: (2025)

Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning
par: Zhang, Wentao, et autres
Publié: (2026)

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning
par: Tang, Yihong, et autres
Publié: (2024)

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
par: Zhao, Yuze, et autres
Publié: (2026)

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
par: Xu, Yige, et autres
Publié: (2026)

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
par: DeepSeek-AI, et autres
Publié: (2025)

AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards
par: Pan, Yiming, et autres
Publié: (2026)

Are VLMs Really Blind
par: Singh, Ayush, et autres
Publié: (2024)

Veracity Bias and Beyond: Uncovering LLMs' Hidden Beliefs in Problem-Solving Reasoning
par: Zhou, Yue, et autres
Publié: (2025)

ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction
par: Guo, Zichun, et autres
Publié: (2026)

Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
par: Liu, Chengzhi, et autres
Publié: (2025)

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
par: Li, Yangfu, et autres
Publié: (2025)

Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
par: Zhou, Qiji, et autres
Publié: (2024)

Absolute Zero: Reinforced Self-play Reasoning with Zero Data
par: Zhao, Andrew, et autres
Publié: (2025)

Enhancing Chest X-ray Classification through Knowledge Injection in Cross-Modality Learning
par: Yan, Yang, et autres
Publié: (2025)

R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO
par: Yao, Huanjin, et autres
Publié: (2025)

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
par: Hu, Wenbin, et autres
Publié: (2025)

Reinforcing Multimodal Reasoning Against Visual Degradation
par: Liu, Rui, et autres
Publié: (2026)

MiRAGeNews: Multimodal Realistic AI-Generated News Detection
par: Huang, Runsheng, et autres
Publié: (2024)

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
par: Huang, Wenxuan, et autres
Publié: (2025)

Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
par: Liang, Jianxin, et autres
Publié: (2025)

R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
par: He, Minggui, et autres
Publié: (2025)