Cover Image

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Shuang, Guo, Yue, Su, Zhaochen, Li, Yafu, Wu, Yulun, Chen, Jiacheng, Chen, Jiayu, Wang, Weijie, Qu, Xiaoye, Cheng, Yu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
by: Wei, Lai, et al.
Published: (2025)

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
by: He, Zefeng, et al.
Published: (2025)

XSkill: Continual Learning from Experience and Skills in Multimodal Agents
by: Jiang, Guanyu, et al.
Published: (2026)

Characterizing, Evaluating, and Optimizing Complex Reasoning
by: Zhang, Haoran, et al.
Published: (2026)

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
by: Fu, Tingchen, et al.
Published: (2025)

Spotlight on Token Perception for Multimodal Reinforcement Learning
by: Huang, Siyuan, et al.
Published: (2025)

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
by: Li, Yafu, et al.
Published: (2025)

FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization
by: Gui, Runquan, et al.
Published: (2026)

SEE: Continual Fine-tuning with Sequential Ensemble of Experts
by: Wang, Zhilin, et al.
Published: (2025)

VideoSSR: Video Self-Supervised Reinforcement Learning
by: He, Zefeng, et al.
Published: (2025)

Timo: Towards Better Temporal Reasoning for Language Models
by: Su, Zhaochen, et al.
Published: (2024)

From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
by: Luo, Ruilin, et al.
Published: (2026)

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models
by: Song, Mingyang, et al.
Published: (2025)

GEMS: Agent-Native Multimodal Generation with Memory and Skills
by: He, Zefeng, et al.
Published: (2026)

Learning to Reason under Off-Policy Guidance
by: Yan, Jianhao, et al.
Published: (2025)

SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information
by: Sun, Jiashuo, et al.
Published: (2024)

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
by: Qu, Xiaoye, et al.
Published: (2025)

Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?
by: Su, Zhaochen, et al.
Published: (2024)

New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR
by: Wang, Zhilin, et al.
Published: (2026)

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
by: Chen, Shuang, et al.
Published: (2025)

OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
by: Su, Zhaochen, et al.
Published: (2025)

SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring
by: Shen, Chuming, et al.
Published: (2025)

FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
by: He, Zefeng, et al.
Published: (2025)

Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
by: Su, Zhaochen, et al.
Published: (2025)

Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts
by: Zhu, Tong, et al.
Published: (2024)

ExGRPO: Learning to Reason from Experience
by: Zhan, Runzhe, et al.
Published: (2025)

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
by: Chen, Guanxu, et al.
Published: (2025)

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
by: Chen, Kun, et al.
Published: (2025)

EdgeFlow: Fast Cold Starts for LLMs on Mobile Devices
by: Yan, Yongsheng, et al.
Published: (2026)

Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning
by: Wang, Zhilin, et al.
Published: (2025)

Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
by: Huang, Shijue, et al.
Published: (2026)

Demystifying Reinforcement Learning in Agentic Reasoning
by: Yu, Zhaochen, et al.
Published: (2025)

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
by: Su, Zhaochen, et al.
Published: (2024)

From Zero to Hero: Cold-Start Anomaly Detection
by: Reiss, Tal, et al.
Published: (2024)

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
by: Wu, Wenhao, et al.
Published: (2026)

Rethinking Entropy Regularization in Large Reasoning Models
by: Jiang, Yuxian, et al.
Published: (2025)

LatentMem: Customizing Latent Memory for Multi-Agent Systems
by: Fu, Muxin, et al.
Published: (2026)

Perception-Aware Policy Optimization for Multimodal Reasoning
by: Wang, Zhenhailong, et al.
Published: (2025)

Keys to Robust Edits: from Theoretical Insights to Practical Advances
by: Yan, Jianhao, et al.
Published: (2024)

Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning
by: Qu, Xiaoye, et al.
Published: (2024)