多智能体金融咨询中检索增强生成与确定性税费计算的对比：一项2×2析因实验

中文摘要 AI 辅助

税费损失收割对长期投资组合增长具有持续益处，但其高效实施往往涉及针对投资组合内持仓及持有人的复杂考量。我们引入定制资本收益计算引擎，以及存储市场咨询报告的RAG检索向量库，为多智能体交易推荐系统提供上下文支撑。我们研究各上下文提供方对推荐质量的影响，以投资组合清算期间产生的相对资本收益为衡量指标。2×2重复测量方差分析（ANOVA）显示，税费优化引擎存在显著主效应：启用该引擎时，相较于无引擎条件，税费节省减少约55个百分点。RAG的主效应不显著，交互效应亦不显著。仅RAG条件下税费节省的描述性均值最高（47.7%），基线条件次之（30.6%），表明预训练语言模型的内化金融知识足以胜任无需显式工具的税费损失收割推荐任务。这些结果显示，为大语言模型（LLM）智能体配备领域特定计算引擎并不能保证性能提升，反而可能引入冲突的优化信号。

英文摘要

Tax-loss harvesting demonstrates consistent benefits to long-term portfolio growth; yet implementing it efficiently often involves complex considerations that are specific to the holdings within that portfolio and the individual who owns it. We introduce a custom capital gains calculation engine and a RAG-retrieved vector store of market advisory reports to provide context for a multi-agent trade recommendation system. We investigate the effects of each context provider on the quality of recommendations, measured by relative capital gains incurred during portfolio liquidation. A 2x2 repeated-measures ANOVA revealed a significant main effect of the tax optimization engine ($F(1,29) = 9.17$, $p = .005$, $η^2_p = .240$): enabling the engine reduced tax savings by approximately 55 percentage points relative to the no-engine conditions. The RAG main effect was not significant ($p = .841$), nor was the interaction ($p = .553$). The RAG-only condition achieved the highest descriptive mean tax savings (47.7%), and the baseline condition performed second-best (30.6%), suggesting that the pre-trained language model's internalized financial knowledge may be sufficient for competent tax-loss harvesting recommendations without explicit tooling. These results indicate that augmenting LLM agents with domain-specific computation engines does not guarantee improved performance and may introduce conflicting optimization signals.

发表机构

• Royal Bank of Canada（加拿大皇家银行）
• RBC Borealis

机构由 AI 辅助整理，请以论文原文为准。