Resisting Manipulative Bots in Memecoin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning
Yichen Luo, Yebo Feng, Jiahua Xu, Yang Liu
TL;DR
The paper tackles manipulation in meme-coin copy trading by introducing an explainable, multi-agent system that uses few-shot chain-of-thought prompting and multi-modal data. It decomposes the task into meme-coin evaluation, wallet (kol) evaluation, wealth management, and order execution, incorporating algorithmic detection of launch bundles, bump, and comment bots. On a dataset of approximately $1{,}000$–$4{,}000$ meme-coin projects, the framework achieves precision in identifying high-potential coins around 70–73%, with wallet-level precision near 70%, and reports over $500{,}000$ in profit from selected KOL wallets. The study demonstrates that LLM-powered, cooperative agents can outperform single-model approaches in volatile, information-rich meme markets, highlighting practical implications for safer, explainable copy trading and bot detection.
Abstract
The launch of \$Trump coin ignited a wave in meme coin investment. Copy trading, as a strategy-agnostic approach that eliminates the need for deep trading knowledge, quickly gains widespread popularity in the meme coin market. However, copy trading is not a guarantee of profitability due to the prevalence of manipulative bots, the uncertainty of the followed wallets' future performance, and the lag in trade execution. Recently, large language models (LLMs) have shown promise in financial applications by effectively understanding multi-modal data and producing explainable decisions. However, a single LLM struggles with complex, multi-faceted tasks such as asset allocation. These challenges are even more pronounced in cryptocurrency markets, where LLMs often lack sufficient domain-specific knowledge in their training data. To address these challenges, we propose an explainable multi-agent system for meme coin copy trading. Inspired by the structure of an asset management team, our system decomposes the complex task into subtasks and coordinates specialized agents to solve them collaboratively. Employing few-shot chain-of-though (CoT) prompting, each agent acquires professional meme coin trading knowledge, interprets multi-modal data, and generates explainable decisions. Using a dataset of 1,000 meme coin projects' transaction data, our empirical evaluation shows that the proposed multi-agent system outperforms both traditional machine learning models and single LLMs, achieving 73% and 70% precision in identifying high-quality meme coin projects and key opinion leader (KOL) wallets, respectively. The selected KOLs collectively generated a total profit of \$500,000 across these projects.