WebCryptoAgent: Agentic Crypto Trading with Web Informatics
Ali Kurban, Wei Luo, Liangyu Zuo, Zeyu Zhang, Renda Han, Zhaolu Kang, Hao Tang
TL;DR
WebCryptoAgent addresses the challenge of robust short-horizon crypto trading by fusing web-informed signals with market data through a vertical two-tier architecture. It couples strategic LLM reasoning on a contextual evidence document with a fast second-tier shock guard and a memory-based Contextual Reflection and Experience Replay loop to continuously improve decisions without retraining. Empirical results across BTCUSDT, ETHUSDT, and POLUSDT show improved stability, reduced spurious activity, and better tail-risk handling relative to baselines. The work offers a practical blueprint for deploying reflective, memory-augmented agents in high-volatility financial settings and may extend to real-time market monitoring beyond crypto.
Abstract
Cryptocurrency trading increasingly depends on timely integration of heterogeneous web information and market microstructure signals to support short-horizon decision making under extreme volatility. However, existing trading systems struggle to jointly reason over noisy multi-source web evidence while maintaining robustness to rapid price shocks at sub-second timescales. The first challenge lies in synthesizing unstructured web content, social sentiment, and structured OHLCV signals into coherent and interpretable trading decisions without amplifying spurious correlations, while the second challenge concerns risk control, as slow deliberative reasoning pipelines are ill-suited for handling abrupt market shocks that require immediate defensive responses. To address these challenges, we propose WebCryptoAgent, an agentic trading framework that decomposes web-informed decision making into modality-specific agents and consolidates their outputs into a unified evidence document for confidence-calibrated reasoning. We further introduce a decoupled control architecture that separates strategic hourly reasoning from a real-time second-level risk model, enabling fast shock detection and protective intervention independent of the trading loop. Extensive experiments on real-world cryptocurrency markets demonstrate that WebCryptoAgent improves trading stability, reduces spurious activity, and enhances tail-risk handling compared to existing baselines. Code will be available at https://github.com/AIGeeksGroup/WebCryptoAgent.