Coinvisor: An RL-Enhanced Chatbot Agent for Interactive Cryptocurrency Investment Analysis

TL;DR

Coinvisor is a reinforcement learning-enhanced chatbot that offers real-time, multi-step analytical support for cryptocurrency investors by integrating diverse data sources and tools, significantly improving tool selection accuracy and user satisfaction.

Contribution

The paper introduces a novel RL-based multi-agent framework for cryptocurrency analysis, enabling dynamic data integration and multi-step reasoning in chatbots, which surpasses existing static models.

Findings

40.7% increase in recall for tool calling accuracy

26.6% improvement in F1 score over base models

High user satisfaction with 4.64/5 rating

Abstract

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).