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 →