arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.03015cs.AI
收藏

超越预测:预测市场代理中的信念到交易层

Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents

Hong Kong University of Science and Technology(香港科学与技术大学);The University of Hong Kong(香港大学);Massachusetts Institute of Technology(麻省理工学院)

Yishu Wang, Yuxuan Wang, Jiaqi Deng, Hanyang Tang

AI总结:

以预测未来事件为通用人工智能测试平台,提出Raven-Agent这一预测市场自主交易代理,在存档决策集的控制重放中表现出色。

摘要:

预测未来事件作为通用人工智能的测试平台受到越来越多关注。评估的自然方式是让模型在预测市场中交易。然而,交易需要的不仅仅是预测。最近的基准报告显示校准概率分数与交易结果之间存在很大差距。我们提出了Raven-Agent,据我们所知,这是第一个用于预测市场的自主交易代理。在对存档决策集的受控重放中,我们的架构在所有测试策略中实现了唯一的正回报和唯一的正风险调整回报。我们已在这个https URL上发布了我们的代码。

英文摘要:

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 .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑