← 研踪 PaperTrailarXiv:2611.24133 · v2
Evaluating LIM Trading Agents: A Critical Review of Backtesting Validity and Reporting Practices
首次提交 2026-11-18 17:47
版本更新 2026-11-19 23:10
雷达观测 2026-11-20 14:52
摘要
Large language models (LLMs) are increasingly used in investment research, and many studies report promising historical returns. However, such results are only credible if researchers can demonstrate that the model used only information available at the time, account for how strategies and configurations were selected, and explain how reported returns were generated. We identify six common threats to validity in LLM investment evaluations and apply them to 18 published studies. Across 108 assessments, we find substantial gaps in reporting. No paper fully addresses information timing, model-memory exposure, universe selection, trading costs, or configuration-selection bias. Only four studies provide minimum evidence that results hold across multiple market periods. Our analysis reveals that commonly used safeguards often address different problems than researchers assume. For example, using dated inputs does not guarantee that a pretrained model lacked knowledge of future events, and repeated experimental runs do not correct for strategy-selection bias. We therefore propose an evaluation protocol for future LLM investment research. Rather than judging whether LLMs can generate profits, our study examines whether existing evidence is sufficient to support such claims. We conclude that current reporting practices are generally insufficient for that purpose.
作者备注:Withdrawn by the submitter because not all co-authors agreed to the posting of this preprint
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-19 23:10 · 最新观测版本
Evaluating LIM Trading Agents: A Critical Review of Backtesting Validity and Reporting Practices
Large language models (LLMs) are increasingly used in investment research, and many studies report promising historical returns. However, such results are only credible if researchers can demonstrate that the model used only information available at the time, account for how strategies and configurations were selected, and explain how reported returns were generated. We identify six common threats to validity in LLM investment evaluations and apply them to 18 published studies. Across 108 assessments, we find substantial gaps in reporting. No paper fully addresses information timing, model-memory exposure, universe selection, trading costs, or configuration-selection bias. Only four studies provide minimum evidence that results hold across multiple market periods. Our analysis reveals that commonly used safeguards often address different problems than researchers assume. For example, using dated inputs does not guarantee that a pretrained model lacked knowledge of future events, and repeated experimental runs do not correct for strategy-selection bias. We therefore propose an evaluation protocol for future LLM investment research. Rather than judging whether LLMs can generate profits, our study examines whether existing evidence is sufficient to support such claims. We conclude that current reporting practices are generally insufficient for that purpose.
查看此版本解读 →查看此版本原文 ↗v1 · 2026-11-18 17:47
Evaluating LIM Trading Agents: A Critical Review of Backtesting Validity and Reporting Practices
Large language models (LLMs) are increasingly used in investment research, and many studies report promising historical returns. However, such results are only credible if researchers can demonstrate that the model used only information available at the time, account for how strategies and configurations were selected, and explain how reported returns were generated. We identify six common threats to validity in LLM investment evaluations and apply them to 18 published studies. Across 108 assessments, we find substantial gaps in reporting. No paper fully addresses information timing, model-memory exposure, universe selection, trading costs, or configuration-selection bias. Only four studies provide minimum evidence that results hold across multiple market periods. Our analysis reveals that commonly used safeguards often address different problems than researchers assume. For example, using dated inputs does not guarantee that a pretrained model lacked knowledge of future events, and repeated experimental runs do not correct for strategy-selection bias. We therefore propose an evaluation protocol for future LLM investment research. Rather than judging whether LLMs can generate profits, our study examines whether existing evidence is sufficient to support such claims. We conclude that current reporting practices are generally insufficient for that purpose.
查看此版本解读 →查看此版本原文 ↗