mlsanityData to 14 Oct 2026

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

arXiv 2609.34004 ↗First posted 27 Sep 2026cs.LG cs.AI q-fin.CPcited by 0

On the map: LLM agents and tool use → Financial trading and forecasting agents

Abstract (arXiv)

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 financial agents incorporate historical evidence, yet they provide limited support for preserving issuer-specific chronology under point-in-time constraints and for identifying when historical transitions contribute information beyond the current forecast. We present RICE-Alpha (Reliability-Informed Correction with Event Graphs), a point-in-time stock-scoring framework that separates a history-aware multi-view Base Alpha from a reliability-calibrated residual correction derived from historical event continuation. A Multi-Tier Memory Layer grounds news interpretation in temporally eligible issuer-specific history, while a Typed Event Agent constructs event states whose successor relations are formed within issuers and pooled across firms only after valid local pairing. Matured transitions are calibrated by their empirical reliability, and the resulting graph signal is residualized against the Base Alpha and technical view to obtain the RICE Delta. On daily Nasdaq-100 and Hang Seng Index panels from 2024 to 2026, RICE-Alpha achieves the strongest results among the evaluated LLM-based agents and momentum across four predictive and four portfolio-level metrics. Its ICIR more than doubles that of the strongest baseline, while net Sharpe ratios reach 1.656 and 1.725 in the U.S. and Hong Kong, respectively. U.S. ablations further show significant reductions in IC and RankIC after Holm adjustment when major components are removed. These results indicate that historical event continuation adds incremental information when it is temporally grounded, reliability-calibrated, and introduced as a residual correction to a multi-view forecast.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 48 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

28 of 48 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards5 Jun
  2. 2025Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading6 Oct
  3. 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization21 May
  4. 2025FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading17 Feb
  5. 2024TradingAgents: Multi-Agents LLM Financial Trading Framework28 Dec
  6. 2023FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design23 Nov

Other references · 22

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
  3. 2023BloombergGPT: A Large Language Model for Financecited by 939
  4. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  5. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
  6. 2023FinGPT: Open-Source Financial Large Language Modelscited by 253
  7. 2023Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Modelscited by 129
  8. 2024Human-inspired Episodic Memory for Infinite Context LLMscited by 62
  9. 2023The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challengescited by 59
  10. 2024FonTS: Text Rendering with Typography and Style Controlscited by 40
  11. 2023Generating Synergistic Formulaic Alpha Collections via Reinforcement Learningcited by 39
  12. 2023MASTER: Market-Guided Stock Transformer for Stock Price Forecastingcited by 32
10 more
  1. 2024AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factorscited by 27
  2. 2024MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Predictioncited by 18
  3. 2025Reasoning on Time-Series for Financial Technical Analysiscited by 5
  4. 2026MEME: Modeling the Evolutionary Modes of Financial Marketscited by 2
  5. 2026AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Modelscited by 2
  6. 2026Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrievalcited by 2
  7. 2025Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Soundcited by 1
  8. 2025Structured Event Representation and Stock Return Predictabilitycited by 1
  9. 2026TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Predictioncited by 1
  10. 2026AnySurf: Any Surface Generation with Directed Edgecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs
  2. 2026DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock Research
  3. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting
  4. 2026FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting
  5. 2026Signal or Noise in Multi-Agent LLM-based Stock Recommendations?
  6. 2025MarketSenseAI 2.0: Enhancing Stock Analysis through LLM Agents
  7. 2026Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals
  8. 2026E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning