Cover Image

SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shu, Fangxun, Ye, Yongjie, Liao, Yue, Kang, Zijian, Yin, Weijie, Wang, Jiacong, Liang, Xiao, Yan, Shuicheng, Feng, Chao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SAIL-VL2 Technical Report
by: Yin, Weijie, et al.
Published: (2025)

SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement
by: Yin, Weijie, et al.
Published: (2025)

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
by: Wang, Jiahao, et al.
Published: (2025)

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
by: Mukherjee, Subhojyoti, et al.
Published: (2025)

Sotopia-RL: Reward Design for Social Intelligence
by: Yu, Haofei, et al.
Published: (2025)

Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization
by: Su, Jianghao, et al.
Published: (2025)

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
by: Li, Hongyu, et al.
Published: (2025)

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
by: Fan, Kaixuan, et al.
Published: (2025)

When to Think and When to Look: Uncertainty-Guided Lookback
by: Bi, Jing, et al.
Published: (2025)

RL makes MLLMs see better than SFT
by: Song, Junha, et al.
Published: (2025)

On-Policy RL with Optimal Reward Baseline
by: Hao, Yaru, et al.
Published: (2025)

ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing
by: Li, Hengjia, et al.
Published: (2026)

When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
by: Fan, Mingyuan, et al.
Published: (2026)

Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
by: Zhou, Runlong, et al.
Published: (2024)

Scalable Vision Language Model Training via High Quality Data Curation
by: Dong, Hongyuan, et al.
Published: (2025)

TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference
by: Zhang, Dan, et al.
Published: (2025)

RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
by: Oertell, Owen, et al.
Published: (2024)

When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains
by: Jeddi, Ahmadreza, et al.
Published: (2026)

ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
by: Chen, Jianghao, et al.
Published: (2025)

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
by: Su, Yi, et al.
Published: (2025)

On Designing Effective RL Reward at Training Time for LLM Reasoning
by: Gao, Jiaxuan, et al.
Published: (2024)

RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs
by: Yao, Liang, et al.
Published: (2026)

Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning
by: Liao, Xinyao, et al.
Published: (2025)

Diagnosing and Mitigating System Bias in Self-Rewarding RL
by: Tan, Chuyi, et al.
Published: (2025)

GRIT: Teaching MLLMs to Think with Images
by: Fan, Yue, et al.
Published: (2025)

Scaling RL to Long Videos
by: Chen, Yukang, et al.
Published: (2025)

ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution
by: Huang, Junjie, et al.
Published: (2026)

CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
by: Ni, Zhenyang, et al.
Published: (2026)

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
by: Sun, Yi, et al.
Published: (2026)

RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
by: Sun, Yiyou, et al.
Published: (2025)

RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
by: Tang, Yinzhou, et al.
Published: (2025)

FlowRL: Matching Reward Distributions for LLM Reasoning
by: Zhu, Xuekai, et al.
Published: (2025)

MARBLE: Multi-Aspect Reward Balance for Diffusion RL
by: Zhao, Canyu, et al.
Published: (2026)

ToolRL: Reward is All Tool Learning Needs
by: Qian, Cheng, et al.
Published: (2025)

AgentV-RL: Scaling Reward Modeling with Agentic Verifier
by: Zhang, Jiazheng, et al.
Published: (2026)

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
by: Feng, Xuelu, et al.
Published: (2025)

Unhackable Temporal Rewarding for Scalable Video MLLMs
by: Yu, En, et al.
Published: (2025)

ToRL: Scaling Tool-Integrated RL
by: Li, Xuefeng, et al.
Published: (2025)

ThinkSwitcher: When to Think Hard, When to Think Fast
by: Liang, Guosheng, et al.
Published: (2025)

TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
by: Wu, Jinyang, et al.
Published: (2025)