Cover Image

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Gengwei, Peng, Jie, Tan, Zhen, Qiu, Mufan, Mahjoub, Hossein Nourkhiz, Tadiparthi, Vaishnav, Lee, Kwonjoon, Zhang, Yanyong, Chen, Tianlong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Robust Reasoning through Guided Adversarial Self-Play
by: Li, Shuozhe, et al.
Published: (2026)

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction
by: Shen, Xu, et al.
Published: (2025)

Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication
by: Li, Huao, et al.
Published: (2024)

Symbolic Graph Inference for Compound Scene Understanding
by: Aryan, FNU, et al.
Published: (2024)

In Search of a Lost Metric: Human Empowerment as a Pillar of Socially Conscious Navigation
by: Baddam, Vasanth Reddy, et al.
Published: (2025)

SSR: A Generic Framework for Text-Aided Map Compression for Localization
by: Omama, Mohammad, et al.
Published: (2026)

Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design
by: Zhang, Mohan, et al.
Published: (2025)

GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction
by: Qu, Huaizhi, et al.
Published: (2025)

MR-LDM -- The Merge-Reactive Longitudinal Decision Model: Game Theoretic Human Decision Modeling for Interactive Sim Agents
by: Holley, Dustin, et al.
Published: (2025)

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
by: Goel, Harsh, et al.
Published: (2025)

SMART-Merge Planner: A Safe Merging and Real-Time Motion Planner for Autonomous Highway On-Ramp Merging
by: Mohammadnejad, Toktam, et al.
Published: (2025)

Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs
by: Zhang, Ruichen, et al.
Published: (2025)

Geometry- and Relation-Aware Diffusion for EEG Super-Resolution
by: Yao, Laura, et al.
Published: (2026)

Task-Aware Resolution Optimization for Visual Large Language Models
by: Luo, Weiqing, et al.
Published: (2025)

Dual Control for Interactive Autonomous Merging with Model Predictive Diffusion
by: Knaup, Jacob, et al.
Published: (2025)

Vulnerability-Aware Robust Multimodal Adversarial Training
by: Zhang, Junrui, et al.
Published: (2025)

ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models
by: Zhou, Kaiwen, et al.
Published: (2023)

QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts
by: Li, Pingzhi, et al.
Published: (2024)

Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
by: Ma, Ji, et al.
Published: (2026)

Modeling the Lane-Change Reactions to Merging Vehicles for Highway On-Ramp Simulations
by: Holley, Dustin, et al.
Published: (2024)

SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes
by: Kong, Zhenglun, et al.
Published: (2025)

OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning
by: Ding, Zezhen, et al.
Published: (2025)

Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach
by: Tan, Zhen, et al.
Published: (2024)

GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models
by: Qiu, Mufan, et al.
Published: (2025)

Proactive aggression or passive resistance: A face perspective on why and how illegitimate tasks elicit various counterproductive work behaviours in employees
by: Fubin Jiang, et al.
Published: (2025)

Can Hallucination Correction Improve Video-Language Alignment?
by: Zhao, Lingjun, et al.
Published: (2025)

Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer
by: Qu, Huaizhi, et al.
Published: (2025)

Chreode: A Cell World Model for One-Step Temporal Dynamics and Perturbation Prediction
by: Qiu, Mufan, et al.
Published: (2026)

Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models
by: Lin, Muhan, et al.
Published: (2024)

Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
by: Zhang, Chi, et al.
Published: (2025)

Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
by: Peng, Jie, et al.
Published: (2024)

Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
by: Zhang, Chunhui, et al.
Published: (2025)

ATLS: Automated Trailer Loading for Surface Vessels
by: Abughaida, Amer, et al.
Published: (2024)

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
by: Tan, Zelin, et al.
Published: (2025)

Task-aware Distributed Source Coding under Dynamic Bandwidth
by: Li, Po-han, et al.
Published: (2023)

ViTGAN: Training GANs with Vision Transformers
by: Lee, Kwonjoon, et al.
Published: (2021)

Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learning
by: Lin, Muhan, et al.
Published: (2025)

Understanding Multimodal Hallucination with Parameter-Free Representation Alignment
by: Wang, Yueqian, et al.
Published: (2024)

TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning
by: Huang, Morris Yu-Chao, et al.
Published: (2025)

MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
by: Dong, Bowen, et al.
Published: (2025)