用多智能体和思维链技术对抗 meme 币跟单中的操纵机器人。
Resisting Manipulative Bots in Meme Coin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning
- 基于多模态大模型与思维链推理的多智能体防御系统。
- 在真实市场摩擦下，跟单者平均收益率达每币3%。
- 适合关注去中心化金融安全与自动化交易的开发者。
跟单交易已成为 meme 币市场的主流入市策略。然而，由于市场极度低流动性与高波动性，该策略暴露了可被利用的攻击面：对手方部署操纵型机器人进行抢先交易、隐藏仓位并伪造情绪，大规模榨取新手跟单者的价值。尽管此类行为普遍，但针对机器人操纵的研究仍很匮乏，缺乏有效的防御框架。本文提出一种抗操纵的跟单交易系统，基于多智能体架构，由多模态大语言模型（LLM）驱动，并结合链式思维（CoT）推理。我们的方法在预测准确率上超越零样本及多数统计驱动基线，在经济表现上优于所有基线，在现实市场摩擦下实现每枚 meme 币投资平均 3% 的跟单者回报率。结果表明，基于智能体的防御有效，且交易者盈利具有可预测性，为鲁棒性跟单交易提供了实用基础。
原文摘要 · Abstract (English)
Copy trading has become the dominant entry strategy in meme coin markets. However, due to the market's extremely illiquid and volatile nature, the strategy exposes an exploitable attack surface: adversaries deploy manipulative bots to front-run trades, conceal positions, and fabricate sentiment, systematically extracting value from naïve copiers at scale. Despite its prevalence, bot-driven manipulation remains largely unexplored, and no robust defensive framework exists. We propose a manipulation-resistant copy-trading system based on a multi-agent architecture powered by a multi-modal large language model (LLM) and chain-of-thought (CoT) reasoning. Our approach outperforms zero-shot and most statistic-driven baselines in prediction accuracy as well as all baselines in economic performance, achieving an average copier return of 3% per meme coin investment under realistic market frictions. Overall, our results demonstrate the effectiveness of agent-based defenses and predictability of trader profitability in adversarial meme coin markets, providing a practical foundation for robust copy trading.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。