FLAG-TRADER: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading

Large language models (LLMs) fine-tuned on multimodal financial data have demonstrated impressive reasoning capabilities in various financial tasks. However, they often struggle with multi-step, goal-oriented scenarios in interactive financial markets, such as trading, where complex agentic approaches are required to improve decision-making. To address this, we propose FLAG-TRADER, a unified architecture integrating linguistic processing (via LLMs) with gradient-driven reinforcement learning (RL) policy optimization, in which a partially finetuned LLM acts as the policy network, leveraging pre-trained knowledge while adapting to the financial domain through parameter-efficient fine-tuning. Through policy gradient optimization driven by trading rewards, our framework not only enhances LLM performance in trading but also improves results on other financialdomain tasks. We present extensive empirical evidence to validate these enhancements. To resolve these interconnected challenges, we FLAG-TRADER, a unified architecture integrating linguistic processing (via LLMs) with gradientdriven RL policy optimization, as shown in Figure 1 . This framework advances two synergistic innovations: a parameter-efficient fine-tuning module that jointly encodes temporal market data and tex-