cs.MANov 9, 2026

Agent4Crypto: A Dual-Reflective and Market-Feedback-Aligned LLM-Based Multi-Agent System for Cryptocurrency Trading

Authors: Guangyan Gan, Jiahao Li, Jiashun Wang, Lin William Cong

Organizations: Nanyang Technological University Singapore, Singapore · Tsinghua University Beijing, China · Shanghai University of International Business and Economics Shanghai, China

Abstract

Cryptocurrency markets provide a natural testbed for autonomous AI agents because they are digital-native, high-frequency, and machine-speed environments, yet existing methods often struggle with non-stationary market regimes, opaque decisions, and fixed aggregation rules. In this paper, we propose Agent4Crypto, a dual-reflective and market-feedback-aligned multi-agent system. The framework coordinates specialized agents for data collection, analysis, risk assessment, reflection, and trading, synthesizing heterogeneous signals from prices, indicators, news, and charts in an interpretable decision pipeline. Our central design is a trader-centric decision mechanism: three style-specific trader agents, Aggressive, Neutral, and Conservative, generate candidate actions and natural-language rationales from the same market context, while their influence is learned rather than manually fixed. A PPO-based gating policy dynamically allocates trader weights through a dual-reflective feedback process. One reflection stream evaluates post-trade decision quality from realized portfolio outcomes and distills reusable lessons into a Financial ReasoningBank for retrieval in subsequent trader prompts, while the other estimates trader-level counterfactual contribution, indicating which style has recently aligned better with market movements. The PPO state combines Counterfactual Contribution Memory with market features, previous trader weights, and current trader actions, so trader influence adapts across bull, sideways, and bear regimes. Experiments on BTC, ETH, and XRP show that Agent4Crypto improves total return and Sharpe ratio over traditional strategies, machine learning and reinforcement learning baselines, and existing LLM-based trading systems, demonstrating the value of interpretable trader competition and market-feedback-driven adaptation in volatile cryptocurrency markets.

Figures & tables

Explore similar work

CardsList
  1. WebCryptoAgent: Agentic Crypto Trading with Web Informatics

    Jan 8, 2026Ali Kurban, Wei Luo, Liangyu Zuo +5cryptocurrency tradingAlgorithmic Trading

  2. Can AI Make Money in Crypto? Measuring the Gap from Backtests to Real Markets

    Sep 28, 2026Xingtong Yu, Jiarun Zhou, Guanlin Ding +12cryptocurrency tradingAlgorithmic Trading