AAAI 2026technical0 citations
Multi-Agent Undercover Gaming: Hallucination Removal Through Counterfactual Test for Multimodal Reasoning
Dayong Liang, Xiao-Yong Wei, Changmeng Zheng
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
BibTeX
@inproceedings{aaai2026_multiagentunderc,
title = {Multi-Agent Undercover Gaming: Hallucination Removal Through Counterfactual Test for Multimodal Reasoning},
author = {Dayong Liang and Xiao-Yong Wei and Changmeng Zheng},
booktitle = {AAAI 2026},
year = {2026}
}