Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Yanhui, Liu, Wu, Ming, Haifeng, Wang, Xinru, Yao, Hantao, Zhang, Yongdong
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.28369
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917540427464704
author Sun, Yanhui
Liu, Wu
Ming, Haifeng
Wang, Xinru
Yao, Hantao
Zhang, Yongdong
author_facet Sun, Yanhui
Liu, Wu
Ming, Haifeng
Wang, Xinru
Yao, Hantao
Zhang, Yongdong
contents E-commerce platforms have begun recruiting crowdsourced jurors to adjudicate massive volumes of transaction disputes. Unlike formal legal judgment, E-commerce dispute verdicts require grounding pivotal clues from redundant, multi-round, multimodal evidence and making decisions under flexible platform-specific conventions. These characteristics render existing methods insufficient for this scenario. To bridge this gap, we introduce a pioneering task, E-commerce Dispute Verdicts (EDV), and present VerdictBench, a multimodal benchmark comprising 6,000 real-world cases designed to reflect crowdsourced jury decisions. Building upon this, we propose CyberJurors, a multi-agent framework to clarify the dispute logic and regulate the verdict process. At the individual level, Individual Verdict Chain-of-Thought decomposes the EDV task into four structured reasoning stages, enabling fine-grained clue perception and clarifying causal logic between pivotal clues and the dispute focus. At the collective level, Jury Consensus Verdict simulates multi-round discussion and voting among jurors, while incorporating verdict precedents to mitigate cognitive biases toward either disputant. Experiments on VerdictBench show that CyberJurors outperforms state-of-the-art LLMs, MLLMs, and court simulators, while achieving stronger alignment with real-world jury voting patterns. Code and dataset are available at https://github.com/YanhuiS/CyberJurors and https://huggingface.co/datasets/piggi/VerdictBench.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28369
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict
Sun, Yanhui
Liu, Wu
Ming, Haifeng
Wang, Xinru
Yao, Hantao
Zhang, Yongdong
Artificial Intelligence
Social and Information Networks
J.4; I.2
E-commerce platforms have begun recruiting crowdsourced jurors to adjudicate massive volumes of transaction disputes. Unlike formal legal judgment, E-commerce dispute verdicts require grounding pivotal clues from redundant, multi-round, multimodal evidence and making decisions under flexible platform-specific conventions. These characteristics render existing methods insufficient for this scenario. To bridge this gap, we introduce a pioneering task, E-commerce Dispute Verdicts (EDV), and present VerdictBench, a multimodal benchmark comprising 6,000 real-world cases designed to reflect crowdsourced jury decisions. Building upon this, we propose CyberJurors, a multi-agent framework to clarify the dispute logic and regulate the verdict process. At the individual level, Individual Verdict Chain-of-Thought decomposes the EDV task into four structured reasoning stages, enabling fine-grained clue perception and clarifying causal logic between pivotal clues and the dispute focus. At the collective level, Jury Consensus Verdict simulates multi-round discussion and voting among jurors, while incorporating verdict precedents to mitigate cognitive biases toward either disputant. Experiments on VerdictBench show that CyberJurors outperforms state-of-the-art LLMs, MLLMs, and court simulators, while achieving stronger alignment with real-world jury voting patterns. Code and dataset are available at https://github.com/YanhuiS/CyberJurors and https://huggingface.co/datasets/piggi/VerdictBench.
title CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict
topic Artificial Intelligence
Social and Information Networks
J.4; I.2
url https://arxiv.org/abs/2605.28369