PulseAugur
EN
LIVE 08:43:43

New LLM-Agent Framework Enhances Stock Forecasting with Event Graphs

By PulseAugur Editorial · [1 sources] ·

Researchers have developed RICE-Alpha, a novel framework for stock forecasting that leverages Large Language Models (LLMs) and event graphs. This system improves upon existing LLM agents by explicitly modeling event continuity, information availability, and transition reliability within historical financial data. RICE-Alpha separates a base alpha prediction from a reliability-calibrated residual correction, using a Multi-Tier Memory Layer and a Typed Event Agent to construct event states and their successor relations. Tested on Nasdaq-100 and Hang Seng Index data from 2024-2026, RICE-Alpha demonstrated superior performance compared to baseline LLM agents, achieving significantly higher ICIR and net Sharpe ratios. AI

IMPACT This framework could improve the accuracy and reliability of LLM-based financial forecasting agents by incorporating event continuity and reliability.

RANK_REASON Research paper detailing a new methodology for LLM-agent stock forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New LLM-Agent Framework Enhances Stock Forecasting with Event Graphs

How we ranked this

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper detailing a new methodology for LLM-agent stock forecasting. [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.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Tong Liu, Lanmiao Liu, Xiang Hu ·

    RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting

    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…

RELATED ENTITIES

RELATED TOPICS