← Back to all news
arXiv Machine Learning By Bolin Song (Cornell University), Surui Xiang (United Nations)

When News Gets Old: Portfolio Allocation with Reinforcement Learning and Large Language Models

Read the original on arXiv Machine Learning →

The paper investigates how the age of financial news affects portfolio decisions by comparing reinforcement learning (RL) policies that incorporate timing information with large language model (LLM) approaches that either retain or filter out older news signals. Using an LLM to extract signals from SEC disclosures, the study finds that RL models can respond to timing cues in controlled tests, yet historical returns show no consistent advantage from including such information. In contrast, filtering out older news in the LLM approach yields the highest average net return, achieving 18.43% per year when news delivery is delayed by four weeks, outperforming all RL strategies that used news.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 28

The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?

The study investigates whether adding inference-time reasoning to large language models (LLMs) improves trading performance. Using a controlled experiment across DeepSeek, GPT, and Gemini models, the authors varied reasoning effort while keeping other variables constant and evaluated over a full year of U.S. equities under three input conditions. Results show that additional reasoning does not reliably increase net portfolio returns and can even lead to nonmonotonic performance and unstable outcomes.

By Jiayi Chen, Guiling Wang
llms
More like this →
arXiv AI
Oct 16

Plan Before You Trade: Inference-Time Optimization for RL Trading Agents

FinPILOT is a plugin inference‑time policy optimization framework that enhances pretrained reinforcement‑learning trading agents by leveraging a multi‑step price forecaster to generate imagined market trajectories. At each decision point, it optimizes the pretrained policy using the forecaster’s predicted price path before executing a trade, without altering the original training pipeline. Across five pretrained policies and multiple market settings, FinPILOT consistently improves total return and Sharpe ratio, with gains increasing as forecast accuracy improves.

By Eun Go, Rohan Deb, Arindam Banerjee
agentsreinforcement-learning
More like this →
arXiv AI
Sep 10

Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning

Alpha‑R1 introduces a reinforcement‑learning aligned large language model framework that performs context‑aware alpha screening by semantically gating candidate factors against a dynamic market state description. The model, trained with group relative policy optimization using realized portfolio returns as reward, selects a sparse subset of factors whose economic rationale matches current market conditions. In a 12‑month out‑of‑sample test, Alpha‑R1 achieved annualized returns of 47.87% on the S&P 500 and 40.57% on the CSI 300, with Sharpe ratios of 1.62 and 2.23, demonstrating the effectiveness of semantic factor reranking in non‑stationary markets.

By Zuoyou Jiang, Li Zhao, Rui Sun, Ruohan Sun, Zhongjian Li, Jing Li, Daxin Jiang, Zuo Bai, Cheng Hua
llmsragreinforcement-learning
More like this →