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

TL;DR

This paper introduces Multi-agent Undercover Gaming (MUG), a novel framework that detects hallucinations in multimodal reasoning by employing counterfactual tests and active, cross-evidence reasoning among agents.

Contribution

MUG advances multi-agent debate by integrating counterfactual testing and active reasoning to improve hallucination detection and multimodal reasoning reliability.

Findings

Enhanced hallucination detection accuracy

Improved multimodal reasoning robustness

Effective identification of hallucinating agents

Abstract

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.