Imagen de Portada

Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jia, Mengzhao, Zhang, Zhihan, Jiang, Meng
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
por: Jia, Mengzhao, et al.
Publicado: (2025)

Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
por: Zhang, Zhihan, et al.
Publicado: (2024)

Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training
por: Jia, Mengzhao, et al.
Publicado: (2024)

MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring
por: Yang, Tengchao, et al.
Publicado: (2025)

MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems
por: Zhu, Zifeng, et al.
Publicado: (2024)

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
por: Wu, Zhenyu, et al.
Publicado: (2024)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
por: Wen, Xumeng, et al.
Publicado: (2025)

PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning
por: Zhang, Zhihan, et al.
Publicado: (2023)

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction
por: Zhang, Chen, et al.
Publicado: (2026)

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
por: Xu, Zhichao, et al.
Publicado: (2025)

Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks
por: Jia, Mengzhao, et al.
Publicado: (2024)

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
por: Liu, Zheyuan, et al.
Publicado: (2024)

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection
por: Hu, Zhengyu, et al.
Publicado: (2026)

From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought
por: Tan, Wentao, et al.
Publicado: (2025)

LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
por: Xu, Jundong, et al.
Publicado: (2025)

DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry
por: Cai, Zhenyang, et al.
Publicado: (2025)

Large Language Models Can Self-Correct with Key Condition Verification
por: Wu, Zhenyu, et al.
Publicado: (2024)

Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning
por: Rajaee, Sara, et al.
Publicado: (2025)

DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning
por: Wu, Yuanhao, et al.
Publicado: (2025)

TOWER: Tree Organized Weighting for Evaluating Complex Instructions
por: Ziems, Noah, et al.
Publicado: (2024)

Knowing When Not to Answer: Evaluating Abstention in Multimodal Reasoning Systems
por: Madhusudhan, Nishanth, et al.
Publicado: (2026)

GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning
por: Zhang, Jianghangfan, et al.
Publicado: (2025)

Reliable Reasoning Beyond Natural Language
por: Borazjanizadeh, Nasim, et al.
Publicado: (2024)

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
por: Peng, Hao, et al.
Publicado: (2025)

Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
por: Kim, Wonjoong, et al.
Publicado: (2025)

HiMed: Incentivizing Hindi Reasoning in Medical LLMs
por: Jiang, Dingfeng, et al.
Publicado: (2026)

Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning
por: Oh, Jungsuk, et al.
Publicado: (2025)

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
por: Huang, Wenxuan, et al.
Publicado: (2025)

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
por: Kim, Kyuyoung, et al.
Publicado: (2026)

Triviality Corrected Endogenous Reward
por: Wang, Xinda, et al.
Publicado: (2026)

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
por: Han, Tianyang, et al.
Publicado: (2026)

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

Unlocking Multimodal Mathematical Reasoning via Process Reward Model
por: Luo, Ruilin, et al.
Publicado: (2025)

VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
por: Wang, Weiyun, et al.
Publicado: (2025)

Refining Answer Distributions for Improved Large Language Model Reasoning
por: Pal, Soumyasundar, et al.
Publicado: (2024)

Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
por: Yan, Shiqi, et al.
Publicado: (2026)

R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
por: He, Minggui, et al.
Publicado: (2025)

Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning
por: Wang, Weiqin, et al.
Publicado: (2025)

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
por: Yue, Yang, et al.
Publicado: (2025)

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
por: Ouyang, Siru, et al.
Publicado: (2024)