用大模型分析社区讨论，实现虚拟皮肤交易自动化。
CSTrader: A Testbed for Language-Grounded Trading in a Community-Driven Virtual Asset Market
- 构建多智能体系统，融合文本、行情与市场规则做决策。
- 在高波动市场中实现最高7.58%收益，优于大盘下跌15.62%。
- 适合研究语言转行动、量化交易与智能体协作的开发者。
小众资产市场如《反恐精英2》武器皮肤市场，规模小、波动大，且受社区讨论和平台规则强烈影响。这类特性使传统量化模型难以适用，却为研究大语言模型如何将非结构化文本转化为交易行为提供了理想场景。本文提出CSTrader，一个面向CS2皮肤市场的语言驱动多智能体交易框架。系统首先整合来自多方的异构信号，再通过专门设计的智能体完成技术分析、流动性评估、事件响应及（逆向）情绪分析，并结合风险控制、交易摩擦与投资组合管理智能体，在真实交易摩擦下生成买入、卖出或持有决策。我们基于高波动时期的实时数据构建了类实战评估环境，对多个近期主流LLM模型进行测试。结果表明，CSTrader在所有模型中均优于下跌15.62%的市场基准及简单单提示基线，实现最高7.58%累计收益并保持可控风险。消融实验显示，流动性、逆向情绪与交易摩擦智能体是将嘈杂文本信号转化为稳定利润的关键，表明小众语言驱动市场可作为未来语言到行动研究的重要基准。代码已开源：https://github.com/IatomicreactorI/CSGOTrading?tab=readme-ov-file#quick-start
原文摘要 · Abstract (English)
Niche asset markets, such as Counter-Strike 2 (CS2) weapon skins, are small, volatile, and heavily driven by community discussions and platform rules. These properties make them hard for traditional quantitative models, but provide an ideal testbed for studying how large language models (LLMs) turn unstructured text into trading actions. We present CSTrader, a multi-agent framework for language-grounded trading in the CS2 skin market. The system first integrates heterogeneous signals from various sources, then uses specialized agents for technical analysis, liquidity, events, and (reversed) sentiment, and finally applies risk control, transaction friction, and portfolio management agents to produce buy, sell, or hold decisions under realistic trading frictions. We build a live-like evaluation environment with real CS2 data from a highly volatile period and evaluate several recent LLM backbones. Across models, CSTrader consistently outperforms both a falling market index (-15.62%) and simple single-prompt LLM baselines, achieving up to a 7.58% cumulative return with controlled risk. Ablation studies show that liquidity, reversed sentiment, and transaction friction agents are crucial for turning noisy language signals into stable profits, suggesting that niche, language-driven markets are a useful benchmark for future language-to-action research. Code is available at: https://github.com/IatomicreactorI/CSGOTrading?tab=readme-ov-file#quick-start
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。