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

Paper: arXiv 2601.08641

Authors: Yichen Luo, Yebo Feng, Jiahua Xu, Yang Liu

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.

Complexity vs Empirical Score

• Math Complexity: 2.0/10
• Empirical Rigor: 6.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper introduces a novel multi-agent LLM system with conceptual rigor but minimal advanced mathematics, relying instead on algorithmic design and prompting strategies; it demonstrates empirical rigor through a backtest on a dataset of 1,000 meme coin projects, reporting specific performance metrics and realized profit figures.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Resisting Manipulative Bots in<br>Meme Coin Copy Trading"] --> B["Data Input:<br>1,000 Meme Coin Project<br>Transaction Datasets"]
  B --> C["Methodology:<br>Multi-Agent System with<br>Chain-of-Thought Prompting"]
  C --> D["Computational Process:<br>Decomposition of task into<br>subtasks by specialized agents"]
  D --> E["Outcome 1:<br>73% Precision in<br>Identifying High-Quality Projects"]
  D --> F["Outcome 2:<br>70% Precision in<br>Identifying KOL Wallets"]
  E --> G["Final Outcome:<br>$500,000 Total Profit<br>Generated by Selected KOLs"]
  F --> G

Cited References (147)

1. A Midsummer Meme’s Dream: Investigating Market Manipulations in the Meme Coin Ecosystem — → 2507.01963
2. A New Wolf in Town? Pump-and-Dump Manipulation in Cryptocurrency Markets (2023)
3. A Survey of Confidence Estimation and Calibration in Large Language Models (2024)
4. A Unified Approach to Interpreting Model Predictions (2017)
5. Advanced Smart Contract Vulnerability Detection via LLM-Powered Multi-Agent Systems (2025)
6. AiRacleX: Automated Detection of Price Oracle Manipulations via LLM-Driven Knowledge Mining and Prompt Generation (2025) — link
7. AMM-based DEX on the XRP Ledger (2025)
8. An analysis of crypto scams during the Covid-19 pandemic: 2020-2022 (2023) — link

8 of 147 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.