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

2025-10-20

AI Summary

Cryptocurrency investment decisions face challenges stemming from extreme market volatility and fragmented information sources; existing approaches exhibit notable limitations in real-time responsiveness, multi-step reasoning, and coordinated utilization of heterogeneous tools. This paper proposes a dynamic decision-making framework based on multi-agent collaboration, innovatively integrating large language models (LLMs), reinforcement learning–driven tool selection, and real-time fusion of multi-source data—including market prices and on-chain metrics—to enable interactive analysis and interpretable, multi-step planning. Compared to static LLMs and generic platforms, automated evaluation demonstrates a 26.6% improvement in tool-call F1 score and a 40.7% increase in recall. A user study yields a satisfaction rating of 4.64/5—significantly outperforming baseline methods—validating the framework’s efficacy, usability, and explanatory power in complex, time-sensitive cryptocurrency investment scenarios.

Technology Category

• Multiagent Systems: Mechanism Design
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Security and Privacy: Cryptocurrency and smart contracts
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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).

Problem

• Addresses cryptocurrency investment challenges through interactive chatbot
• Overcomes fragmented data and volatility with multi-agent framework
• Enhances real-time analysis via reinforcement learning tool selection

Innovation

• Reinforcement learning-based tool selection mechanism
• Multi-agent framework integrating diverse analytical capabilities
• Real-time interaction with adaptive dynamic content analysis