Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning

arXiv:2511.11182 · cs.AI, cs.CL, cs.MA, cs.MM · Submitted 2025-11-14 · Read on arXiv

cs.AI, cs.CL, cs.MA, cs.MM

Submitted: 2025-11-14

Updated: 2026-10-10

Code: https://github.com/YongLD/MUG

Terminology

• Hallucination — 4× in this paper · explained in 4 episodes
• Multimodal Reasoning — 3× in this paper · explained in 5 episodes
• Multi-agent Undercover Gaming — 2× in this paper
• Although the Multi-Agent Debate — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Causal Agent based on Large Language Model
• GPT-4o System Card
• LLaVA-OneVision: Easy Visual Task Transfer
• Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
• A Survey on Hallucination in Large Vision-Language Models
• Step1X-Edit: A Practical Framework for General Image Editing
• DeepSeek-VL: Towards Real-World Vision-Language Understanding
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems