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

arXiv: https://arxiv.org/abs/2511.11182 · HTML: https://mlsanity.com/paper/2511.11182/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 9 of its 44 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 9 of 9)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [Imagine while Reasoning in Space: Multimodal Visualization-of-Thought](https://mlsanity.com/paper/2501.07542/) (2025)
- [Causal Agent based on Large Language Model](https://mlsanity.com/paper/2408.06849/) (2024)

## Built on by (most cited first, 4 of 4)

- [Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing](https://mlsanity.com/paper/2604.08401/) (2026)
- [GIFT: Games as Informal Training for Generalizable LLMs](https://mlsanity.com/paper/2601.05633/) (2026)
- [Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning](https://mlsanity.com/paper/2606.29425/) (2026)
- [DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation](https://mlsanity.com/paper/2608.17282/) (2026)

## Abstract (arXiv)

Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD) paradigm offers a promising solution by promoting consensus among multiple agents to enhance reliability, it relies on the unrealistic assumption that all debaters are rational and reflective, which is a condition that may not hold when agents themselves are prone to hallucinations. To address this gap, we introduce the Multi-agent Undercover Gaming (MUG) protocol, inspired by social deduction games like "Who is Undercover?". MUG reframes MAD as a process of detecting "undercover" agents (those suffering from hallucinations) by employing multimodal counterfactual tests. Specifically, we modify reference images to introduce counterfactual evidence and observe whether agents can accurately identify these changes, providing ground-truth for identifying hallucinating agents and enabling robust, crowd-powered multimodal reasoning. MUG advances MAD protocols along three key dimensions: (1) enabling factual verification beyond statistical consensus through counterfactual testing; (2) introducing cross-evidence reasoning via dynamically modified evidence sources instead of relying on static inputs; and (3) fostering active reasoning, where agents engage in probing discussions rather than passively answering questions. Collectively, these innovations offer a more reliable and effective framework for multimodal reasoning in LLMs. The source code can be accessed at https://github.com/YongLD/MUG.git.