🤖 AI Summary
To address the challenge of detecting human-mimicking, fairness-compromising, and inherently uninterpretable leveling bots in MMORPGs, this paper proposes a human-in-the-loop unsupervised detection framework. Methodologically, it integrates contrastive representation learning with clustering to identify anomalous leveling patterns and—novelty—employs large language models (LLMs) as auxiliary reviewers, generating interpretable decision criteria via growth-curve visualization. The framework establishes an end-to-end detection–explanation–validation闭环 without requiring labeled data and supports scalable deployment. Experiments demonstrate significant improvements over baselines in both detection accuracy and traceability: manual review efficiency increases by 42%. This work introduces a new paradigm for game anti-cheating systems that is robust, transparent, and operationally viable.
📝 Abstract
In Massively Multiplayer Online Role-Playing Games (MMORPGs), auto-leveling bots exploit automated programs to level up characters at scale, undermining gameplay balance and fairness. Detecting such bots is challenging, not only because they mimic human behavior, but also because punitive actions require explainable justification to avoid legal and user experience issues. In this paper, we present a novel framework for detecting auto-leveling bots by leveraging contrastive representation learning and clustering techniques in a fully unsupervised manner to identify groups of characters with similar level-up patterns. To ensure reliable decisions, we incorporate a Large Language Model (LLM) as an auxiliary reviewer to validate the clustered groups, effectively mimicking a secondary human judgment. We also introduce a growth curve-based visualization to assist both the LLM and human moderators in assessing leveling behavior. This collaborative approach improves the efficiency of bot detection workflows while maintaining explainability, thereby supporting scalable and accountable bot regulation in MMORPGs.