PulseAugur
EN
LIVE 03:00:50

LLM Trading Agents Fail to Outperform Simple Bets on Market News

A new arXiv paper investigates the efficacy of large language model (LLM) trading agents in predicting stock market movements around earnings announcements and bad news. The study found that none of the tested LLM agents, including those based on Gemini and GPT models, consistently outperformed simple betting strategies or logistic regression models. The agents' performance was largely attributed to memorized information from their training data rather than genuine predictive capabilities on unseen news. AI

IMPACT LLM agents struggle to find profitable trading strategies based on real-time news, suggesting current capabilities are limited by training data rather than predictive insight.

RANK_REASON The cluster contains a research paper published on arXiv detailing experimental findings. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.MA (Multiagent) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

LLM Trading Agents Fail to Outperform Simple Bets on Market News

How we ranked this

Signal score
2 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a research paper published on arXiv detailing experimental findings. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Jackson Wang ·

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

    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, su…