{"paper_id":"2601.08641","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"],"paper_date":"2026-01-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2601.08641v1","page_url":"https://thequant.space/flowcharts/resisting-manipulative-bots-in-memecoin-copy-trading-a-mult/","scores":{"empirical_rigor":6,"math_complexity":2,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a manipulation‑resistant copy‑trading system using a multi‑agent architecture powered by a multi‑modal LLM and chain‑of‑thought reasoning.","quote":"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.","summary":"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…","strategy":"LLM-powered multi-agent copy‑trading system for meme coins"},"assumptions":{"status":"available","items":[{"assumption":"A strategic adversary can rapidly create and control many on‑chain wallets to manipulate meme coin markets.","type":"model","stated":"explicit","quote":"We assume a strategic adversary capable of rapidly creating and controlling a large number of on-chain wallets."},{"assumption":"Selected KOL wallets possess superior trading expertise or informational advantages, leading to consistent profitability.","type":"market","stated":"explicit","quote":"A key assumption underlying copy trading is that selected KOL wallets possess superior trading expertise or informational advantages, enabling them to achieve consistent profitability."},{"assumption":"Traders pay a 1% transaction fee when buying meme coins on Solana’s pump.fun platform.","type":"execution","stated":"explicit","quote":"Traders purchase meme coins using SOL, Solana’s native cryptocurrency, paying a 1% transaction fee and following a bonding curve mechanism."},{"assumption":"The bonding curve induces a strictly increasing and convex price path, penalising late entry.","type":"market","stated":"explicit","quote":"The bonding curve induces a strictly increasing and convex price path, so prices rise deterministically with cumulative demand, yielding diminishing tokens received per unit of SOL deposited."}]},"datasets":{"status":"available","items":[{"name":"Flipside on-chain transaction and transfer records","provider":"Flipside","kind":"crypto-onchain","access":"public","period":null,"universe":"6,000 meme coin projects","quote":"For on-chain data, we use account-level transaction and transfer records obtained from Flipside, a blockchain data provider that maintains archive nodes with fully indexed, historical access to the Solana ledger."},{"name":"pump.fun off-chain comment data","provider":"pump.fun","kind":"text-news","access":"public","period":null,"universe":"6,000 meme coin projects","quote":"We additionally collect off-chain comment data from pump.fun."}],"known":[],"sample":{"start":null,"end":null,"market":"meme coin market","asset_class":"crypto","frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"1% transaction fee per trade on Solana’s pump.fun platform","quote":"Traders purchase meme coins using SOL, Solana’s native cryptocurrency, paying a 1% transaction fee and following a bonding curve mechanism.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"1% transaction fee per trade on Solana’s pump.fun platform","card_quote":"Traders purchase meme coins using SOL, Solana’s native cryptocurrency, paying a 1% transaction fee and following a bonding curve mechanism.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The proposed multi‑agent system achieves an average copier return of 3% per meme‑coin investment under realistic market frictions.","kind":"performance","quote":"achieving an average copier return of 3% per meme coin investment under realistic market frictions."},{"finding":"Smart‑money wallets identified by the framework generate an average return of 14%.","kind":"performance","quote":"Economically, the smart-money wallets identified by our framework achieve an average return of 14%, while the corresponding estimated copier return is 3% per meme coin investment under realistic market frictions."},{"finding":"The MAS with chain‑of‑thought reasoning attains the highest AUC among models, outperforming zero‑shot and statistic‑driven baselines.","kind":"predictive-accuracy","quote":"the highest AUC overall, followed closely by the MAS with CoT reasoning."},{"finding":"Removing the wallet‑assessment agent causes the largest performance drop, indicating its dominant role over timing and coin‑level agents.","kind":"performance","quote":"removing the timing agent yields a smaller but non-negligible decline."}],"reported_performance":{"strategy":"LLM-powered multi-agent copy‑trading system for meme coins","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":28,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:16:12Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}