Coinvisor: An RL-Enhanced Chatbot Agent for Interactive Cryptocurrency Investment Analysis
This addresses the need for more effective and adaptive analysis tools for cryptocurrency investors, though it is incremental as it builds on existing multi-agent and RL methods for a specific domain.
The paper tackles the problem of fragmented information and high volatility in cryptocurrency investment by developing Coinvisor, an RL-enhanced chatbot agent that integrates real-time data and multi-step reasoning, resulting in a 40.7% recall improvement and 26.6% F1 score gain over the base model in tool orchestration, with high user satisfaction (4.64/5).
The cryptocurrency market offers significant investment opportunities but faces challenges including high volatility and fragmented information. Data integration and analysis are essential for informed investment decisions. Currently, investors use three main approaches: (1) Manual analysis across various sources, which depends heavily on individual experience and is time-consuming and prone to bias; (2) Data aggregation platforms-limited in functionality and depth of analysis; (3) Large language model agents-based on static pretrained models, lacking real-time data integration and multi-step reasoning capabilities. To address these limitations, we present Coinvisor, a reinforcement learning-based chatbot that provides comprehensive analytical support for cryptocurrency investment through a multi-agent framework. Coinvisor integrates diverse analytical capabilities through specialized tools. Its key innovation is a reinforcement learning-based tool selection mechanism that enables multi-step planning and flexible integration of diverse data sources. This design supports real-time interaction and adaptive analysis of dynamic content, delivering accurate and actionable investment insights. We evaluated Coinvisor through automated benchmarks on tool calling accuracy and user studies with 20 cryptocurrency investors using our interface. Results show that Coinvisor improves recall by 40.7% and F1 score by 26.6% over the base model in tool orchestration. User studies show high satisfaction (4.64/5), with participants preferring Coinvisor to both general LLMs and existing crypto platforms (4.62/5).