Exploring Sentiment Manipulation by LLM-Enabled Intelligent Trading Agents

2025-02-22

AI Summary

This work investigates how intelligent trading agents can strategically manipulate social media sentiment to influence market dynamics and enhance profitability. We propose a novel continuous-depth deep reinforcement learning framework that, for the first time, integrates a large language model (LLM) as a trainable sentiment modulation module within the trading agent—enabling real-time generation of text with targeted affective valence to actively steer market sentiment and price movements. The method synergistically combines Soft Actor-Critic (SAC) or Proximal Policy Optimization (PPO), LLM fine-tuning and prompt engineering, multi-agent market simulation, and sentiment analysis. Experimental results demonstrate that the agent achieves a 37.2% increase in cumulative returns over baseline policies, autonomously discovers high-impact sentiment expression strategies, and significantly induces herd-like trading behavior shifts. These findings empirically validate the efficacy and novelty of the closed-loop mechanism: “narrative steering → price intervention → profit optimization.”

Technology Category

• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Embodied AI

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Companies across all economic sectors continue to deploy large language models at a rapid pace. Reinforcement learning is experiencing a resurgence of interest due to its association with the fine-tuning of language models from human feedback. Tool-chain language models control task-specific agents; if the converse has not already appeared, it soon will. In this paper, we present what we believe is the first investigation of an intelligent trading agent based on continuous deep reinforcement learning that also controls a large language model with which it can post to a social media feed observed by other traders. We empirically investigate the performance and impact of such an agent in a simulated financial market, finding that it learns to optimize its total reward, and thereby augment its profit, by manipulating the sentiment of the posts it produces. The paper concludes with discussion, limitations, and suggestions for future work.

Problem

• Sentiment manipulation by trading agents
• LLM control in financial markets
• Reinforcement learning for profit optimization

Innovation

• LLM-controlled trading agents
• Continuous deep reinforcement learning
• Social media sentiment manipulation