GuruAgents: Emulating Wise Investors with Prompt-Guided LLM Agents
Yejin Kim, Youngbin Lee, Juhyeong Kim, Yongjae Lee
TL;DR
GuruAgents demonstrate that prompt-guided LLM agents can operationalize the qualitative insights of investment gurus into deterministic, backtestable portfolio rules. By encoding role definitions, quotations, and deterministic scoring into system prompts, the approach yields replicable decision pipelines that produce diversified to highly concentrated portfolios consistent with each guru’s philosophy. The Buffett agent delivers the strongest performance ($42.2\%$ CAGR) among the five, while the others vary, highlighting the influence of prompt design on outcomes. The work shows a new direction for automated systematic investing and provides public code and data for replication.
Abstract
This study demonstrates that GuruAgents, prompt-guided AI agents, can systematically operationalize the strategies of legendary investment gurus. We develop five distinct GuruAgents, each designed to emulate an iconic investor, by encoding their distinct philosophies into LLM prompts that integrate financial tools and a deterministic reasoning pipeline. In a backtest on NASDAQ-100 constituents from Q4 2023 to Q2 2025, the GuruAgents exhibit unique behaviors driven by their prompted personas. The Buffett GuruAgent achieves the highest performance, delivering a 42.2\% CAGR that significantly outperforms benchmarks, while other agents show varied results. These findings confirm that prompt engineering can successfully translate the qualitative philosophies of investment gurus into reproducible, quantitative strategies, highlighting a novel direction for automated systematic investing. The source code and data are available at https://github.com/yejining99/GuruAgents.