[论文解读] FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Yangyang Yu, Haohang Li+7 more|arXiv (Cornell University)|Nov 23, 2023

Stock Market Forecasting Methods被引用 7

一句话总结

FinMem 引入一个模块化的基于LLM的交易智能体，具备个性化 Profiling、分层记忆与自适应角色设计，以提升股票交易绩效，实现记忆驱动的决策与对市场信号的快速适应。

ABSTRACT

Recent advancements in Large Language Models (LLMs) have exhibited notable efficacy in question-answering (QA) tasks across diverse domains. Their prowess in integrating extensive web knowledge has fueled interest in developing LLM-based autonomous agents. While LLMs are efficient in decoding human instructions and deriving solutions by holistically processing historical inputs, transitioning to purpose-driven agents requires a supplementary rational architecture to process multi-source information, establish reasoning chains, and prioritize critical tasks. Addressing this, we introduce extsc{FinMem}, a novel LLM-based agent framework devised for financial decision-making. It encompasses three core modules: Profiling, to customize the agent's characteristics; Memory, with layered message processing, to aid the agent in assimilating hierarchical financial data; and Decision-making, to convert insights gained from memories into investment decisions. Notably, extsc{FinMem}'s memory module aligns closely with the cognitive structure of human traders, offering robust interpretability and real-time tuning. Its adjustable cognitive span allows for the retention of critical information beyond human perceptual limits, thereby enhancing trading outcomes. This framework enables the agent to self-evolve its professional knowledge, react agilely to new investment cues, and continuously refine trading decisions in the volatile financial environment. We first compare extsc{FinMem} with various algorithmic agents on a scalable real-world financial dataset, underscoring its leading trading performance in stocks. We then fine-tuned the agent's perceptual span and character setting to achieve a significantly enhanced trading performance. Collectively, extsc{FinMem} presents a cutting-edge LLM agent framework for automated trading, boosting cumulative investment returns.

研究动机与目标

• 提出需要能够处理多源、时效性各异的金融数据的自主智能体的必要性。
• 提出 FinMem 的三模块架构（Profiling、Memory、Decision-making），以应对 DRL 与以往 LLM 智能体在记忆与可解释性方面的局限。
• 展示分层记忆与自适应字符设置如何在波动市场中改进交易决策与鲁棒性。
• 表明 FinMem 在训练数据有限、以及使用通用型LLM的真实数据集上实现更优的交易表现。

提出的方法

• 引入 FinMem 的 Profiling 模块以自定义智能体特征与风险倾向。
• 开发 Memory 模块，具备工作记忆与分层的长期记忆以处理时效性信息。
• 定义将记忆派生洞见转化为交易行动（买/卖/观望）的决策模块。
• 采用一种新的记忆评分函数，综合近时性、相关性与重要性，覆盖浅层、中间层、深层。
• 从各层提取 Top-K 记忆事件以指导即时与延展的反思，从而引导交易决策。
• 以分层衰减机制和访问计数器对记忆更新与保留进行约束，优先处理关键事件。

Figure 1: The prompt template for FinMem ’s profiling module. It includes two key elements of its character setting: professional background knowledge and three distinct investment risk inclinations. In the self-adaptive risk inclination option, the omitted texts align with the detailed descriptions

实验结果

研究问题

• RQ1 RQ1：FinMem 在真实世界数据上是否优于当代算法交易智能体？
• RQ2 RQ2：是否存在对其他交易算法具有挑战性但 FinMem 能够胜任的任务？
• RQ3 RQ3：哪种LLM骨干模型能为 FinMem 提供最佳性能？
• RQ4 RQ4：不同交易者的风险倾向是否会显著区分 FinMem 的交易表现？
• RQ5 RQ5：FinMem 是否能够有效过滤与优先排序信息以辅助交易决策？

主要发现

• FinMem 在可扩展的真实世界数据集上相对于代表性算法智能体显示出领先的交易表现。
• FinMem 的记忆与 Profiling 模块使市场洞察的分层与利用更为高效，提升决策质量。
• 调整骨干 LLM、工作记忆容量与角色设置对交易性能有显著影响。
• 动态风险倾向特性使 FinMem 能适应市场条件并降低下行风险。
• 消融研究表明 FinMem 能从 past trading experiences 学习并通过市场互动演化其知识库。
• 该框架在数据有限（数日到数月）的情况下实现稳健的交易表现，并在更大数据集与专门的金融 LLM 下仍具潜力。

Figure 2: Memory module structure of FinMem with a detailed view of components, operations, and workflow. The cognitive architectures of FinMem ’s memory module have two core components – Working Memory and Layered Long-term Memory.