首个自主预测市场交易代理，突破单纯预测局限
Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents
- 构建自主交易代理Raven-Agent，融合信念与行动决策
- 在历史数据回放中唯一实现正收益与正风险调整收益
- 适合关注AI决策能力评估与量化交易的读者
预测未来事件已成为通用人工智能的重要测试场景。将模型置于预测市场中进行交易，是验证其能力的有效方式。然而，交易不仅需要预测，还需策略与风险管理。当前基准显示，概率校准分数与实际交易表现间存在显著差距。本文提出Raven-Agent，据我们所知是首个面向预测市场的自主交易代理。在对归档决策数据的受控回放中，该架构在所有测试策略中唯一实现正回报和正风险调整回报。代码已开源：https://github.com/Alchemist-X/predict-raven。
原文摘要 · Abstract (English)
Forecasting future events has attracted growing attention as a testbed for general-purpose AI. A natural way to ground this evaluation is let the models trade in the prediction markets. Trading, however, requires more than forecasting. Moreover, recent benchmarks report a substantial gap between calibrated probability scores and the trading results. We propose Raven-Agent, to the best of our knowledge, the first autonomous trading agent for prediction markets. On a controlled replay over an archived decision set, our architecture achieves the only positive return and the only positive risk-adjusted return among all tested policies. We have released our code in https://github.com/Alchemist-X/predict-raven .
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。