跳到正文
arXiv cs.AI· Jackson Wang·· 56 分钟前精选AI 评分60

arXiv 论文测试 LLM 交易智能体在财报与坏消息后的表现:唯一优势来自训练期记忆

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

AI 导读

arXiv 论文(arXiv:2611.22177)用无前视基准测试 LLM 交易智能体,覆盖 598 次财报公布前和 409 次大盘股坏消息下跌后两个时点,四个厂商的五个模型没有一个跑赢简单规则。

推荐理由

论文用无前视基准检验 LLM 交易智能体在财报与坏新闻后的表现,给出的盲测方法可直接用于同类评估。

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