English(EN) RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting

新的LLM智能体框架利用事件图增强股票预测能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 04:00

研究人员开发了RICE-Alpha，一个利用大型语言模型（LLM）和事件图进行股票预测的新型框架。该系统通过显式建模历史金融数据中的事件连续性、信息可用性和转换可靠性，改进了现有的LLM智能体。RICE-Alpha将基础阿尔法预测与可靠性校准的残差校正分开，使用多层记忆层和类型事件智能体来构建事件状态及其后继关系。在2024-2026年的纳斯达克100指数和恒生指数数据上进行测试，RICE-Alpha相比基线LLM智能体表现出更优越的性能，实现了显著更高的ICIR和净夏普比率。 AI

影响该框架通过整合事件连续性和可靠性，有望提高基于LLM的金融预测智能体的准确性和可靠性。

排序理由研究论文，详细介绍了一种用于LLM智能体股票预测的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了一种用于LLM智能体股票预测的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Tong Liu, Lanmiao Liu, Xiang Hu · 2026-10-02 04:00

RICE-Alpha：基于可靠性信息的事件图校正用于LLM-Agent股票预测

arXiv:2609.34004v2 Announce Type: replace Abstract: Equity-relevant news evolves through temporally dependent corporate events, making historical information useful only when event continuity, information availability, and transition reliability are modeled. Existing LLM-based fi…

本文如何被排名

报道来源 [1]

RICE-Alpha：基于可靠性信息的事件图校正用于LLM-Agent股票预测

相关实体

相关话题