跳到正文
arXiv cs.AI· Jackson Wang·· 4 小时前AI 评分38

LLM 交易智能体在财报发布前与坏消息后的表现:唯一优势来自训练记忆

The Only Edge Was Memorized in Training: LLM Trading Agents Around Earnings and Bad News

AI 导读

在无前视偏差的基准上测试四个厂商五个 LLM 交易智能体,分别针对 598 次财报公告前和 409 次坏消息下跌后的决策,没有任何智能体跑赢简单下注策略。财报前智能体大多选择买入,收益等同于每次公告前无差别买入;坏消息后基于 Gemini 的智能体几乎把所有下跌都判为过度反应,也没有智能体比全部抄底选得更准。

正文 · 原文

View PDF HTML (experimental)

Abstract:Large language model (LLM) trading agents are tested on news, but news reaches stock prices within minutes, and a benchmark that replays headlines at their publication time finds no alpha in trading on them. Money can then remain in two places, before news whose date is known, such as earnings announcements, and after bad news, if the market's fall went too far. However, studies of LLMs and earnings read documents published with or after the announcement, and studies of reversal sort monthly portfolios, so neither tells whether an agent can trade these moments after costs. In this paper, we test LLM agents at both moments on the same look-ahead-free benchmark, before 598 earnings announcements and after 409 bad-news drops of large US stocks. Every input is cut at the decision close, staged agents are compared with single calls, simple rules and a logistic regression, and every decision is made with and without the stock's name. Across five models from four vendors, no agent beat the simple bets. Before earnings, the agents mostly bought and earned what buying before every announcement earned, and after bad news, a Gemini-based agent called almost every fall an overreaction while no agent picked better dips than buying them all. The only gains came from what the models had memorized in training. Given only the ticker and the dates, a GPT-based model called the direction of 59.2% of the announcements before its training cutoff and 53.3% after it. Agent builders should therefore compare an event agent with the simple bet and test it blind after the training cutoff.
Comments: 21 pages, 9 figures, 12 tables. Original empirical study of LLM trading agents before scheduled earnings announcements and after bad-news drops, run on the rta-bench-1 benchmark (arXiv:2611.19530)
Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
Cite as: arXiv:2611.22177 [cs.AI]
  (or arXiv:2611.22177v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.22177

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jackson Wang [view email]
[v1] Tue, 17 Nov 2026 04:13:18 UTC (306 KB)

来源:arXiv cs.AI · arxiv.org