Resisting Manipulative Bots in Meme Coin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning

TL;DR

This paper introduces a multi-agent, LLM-powered system with chain-of-thought reasoning to defend against manipulative bots in meme coin copy trading, improving prediction accuracy and economic returns.

Contribution

It presents a novel multi-agent framework leveraging large language models and reasoning to detect and resist manipulative trading bots in volatile meme coin markets.

Findings

Outperforms zero-shot and statistic baselines in prediction accuracy

Achieves an average 3% return per meme coin investment

Demonstrates effectiveness of agent-based defenses in adversarial markets

Abstract

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 na\"ive 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.