Resisting Manipulative Bots in Memecoin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning
- URL: http://arxiv.org/abs/2601.08641v1
- Date: Tue, 13 Jan 2026 15:13:41 GMT
- Title: Resisting Manipulative Bots in Memecoin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning
- Authors: Yichen Luo, Yebo Feng, Jiahua Xu, Yang Liu,
- Abstract summary: Copy trading is a strategy-agnostic approach that eliminates the need for deep trading knowledge.<n>We propose an explainable multi-agent system for meme coin copy trading.<n>Our system decomposes the complex task into subtasks and coordinates specialized agents to solve them collaboratively.
- Score: 6.363535820961979
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- MemeTrans: A Dataset for Detecting High-Risk Memecoin Launches on Solana [12.516642041569467]
We introduce MemeTrans, the first dataset for studying and detecting high-risk memecoin launches on Solana.<n>To precisely capture launch patterns, we design 122 features spanning dimensions such as context, trading activity, holding concentration, and time-series dynamics.<n>Experiments on the introduced high-risk launch detection task suggest that designed features are informative for capturing high-risk patterns and ML models trained on MemeTrans can effectively reduce financial loss by 56.1%.
arXiv Detail & Related papers (2026-02-13T21:35:15Z) - MemeChain: A Multimodal Cross-Chain Dataset for Meme Coin Forensics and Risk Analysis [52.468043639056596]
The meme coin ecosystem has grown into one of the most active yet least observable segments of the cryptocurrency market.<n>MemeChain integrates on-chain data with off-chain artifacts, including website HTML source code, token logos, and linked social media accounts.<n>We quantify the ecosystem's extreme volatility, identifying 1,801 tokens (5.15%) that cease all trading activity within just 24 hours of launch.
arXiv Detail & Related papers (2026-01-28T14:42:02Z) - When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents [74.55061622246824]
Agent Market Arena (AMA) is the first lifelong, real-time benchmark for evaluating Large Language Model (LLM)-based trading agents.<n>AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework.<n>It evaluates agents across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash.
arXiv Detail & Related papers (2025-10-13T17:54:09Z) - Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading [57.28635022507172]
TiMi is a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment.<n>We propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection.
arXiv Detail & Related papers (2025-10-06T13:08:55Z) - Meta-Learning Reinforcement Learning for Crypto-Return Prediction [16.344249366257003]
We present Meta-RL-Crypto, a unified transformer-based architecture that unifies meta-learning and reinforcement learning.<n>The agent iteratively alternates between three roles-actor, judge, and meta-judge-in a closed-loop architecture.<n>Experiments across diverse market regimes demonstrate that Meta-RL-Crypto shows good performance on the technical indicators of the real market.
arXiv Detail & Related papers (2025-09-11T14:20:45Z) - A Midsummer Meme's Dream: Investigating Market Manipulations in the Meme Coin Ecosystem [57.92093214580746]
We characterize the tokenomics of meme coins and track their growth in a three-month longitudinal analysis.<n>We find evidence of extensive use of artificial growth strategies designed to create a misleading appearance of market interest.<n>Most of the tokens involved had previously experienced wash trading or LPI, indicating how initial manipulations often set the stage for later exploitation.
arXiv Detail & Related papers (2025-04-16T13:54:42Z) - Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents [69.58565132975504]
Large language models (LLMs) have demonstrated remarkable capabilities in natural language tasks.<n>We present the Agent Trading Arena, a virtual zero-sum stock market in which LLM-based agents engage in competitive multi-agent trading.
arXiv Detail & Related papers (2025-02-25T08:41:01Z) - LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management [9.9661459222949]
We propose an explainable, multi-modal, multi-agent framework for cryptocurrency investment.<n>Our framework uses specialized agents that collaborate within and across teams to handle subtasks such as data analysis, literature integration, and investment decision-making.
arXiv Detail & Related papers (2025-01-01T13:08:17Z) - A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading [1.4356611205757077]
This research focuses on developing a reinforcement learning (RL) framework to tackle the complexities of trading five prominent cryptocurrencys: Coin, Litecoin, Ripple, and Tether.
We present the CausalReinforceNet(CRN) framework, which integrates both Bayesian and dynamic Bayesian network techniques to empower the RL agent in trade decision-making.
We develop two agents using the framework based on distinct RL algorithms to analyse performance compared to the Buy-and-Hold benchmark strategy and a baseline RL model.
arXiv Detail & Related papers (2023-10-14T01:08:52Z) - Pump and Dumps in the Bitcoin Era: Real Time Detection of Cryptocurrency Market Manipulations [50.521292491613224]
We perform an in-depth analysis of pump and dump schemes organized by communities over the Internet.
We observe how these communities are organized and how they carry out the fraud.
We introduce an approach to detect the fraud in real time that outperforms the current state of the art.
arXiv Detail & Related papers (2020-05-04T21:36:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.