Authors - An Dinh Van, Anh Nguyen Thi Linh, Phuong Pham Nguyen Hien, Hung Nguyen Gia, Trinh Tran Thi Kieu, Hung Nguyen Quang Abstract - This study proposes and evaluates a hybrid framework that integrates multi-agent systems and functional architecture for automated financial trading in Vietnam. The framework assigns specialized roles - fundamental, technical, news, market, trader and risk agents - operating over multimodal stock market data (OHLCV, technical indicators, firm fundamentals, and textual news). Agents interact via structured horizontal debates and vertical risk gating to produce auditable trading proposals. Experimental results demonstrate improved risk-adjusted returns and enhanced explainability, while modular design supports deployment for back-office automation (e.g., report generation and opportunity identification). The study contributes a methodology for combining agentic large language model (LLMs) with disciplined functional pipelines and provides practical guidance for deploying such systems in emerging markets characterized by high volatility and limited liquidity. Implications for FinTech adoption and regulatory alignment in Vietnam are discussed. Vin-Trade-Agent is available at https://github.com/thanhENC/Vin-Trade-Agent.
