FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making

TL;DR

FinHEAR is a multi-agent framework that enhances financial decision-making by integrating human expertise, behavioral economics principles, and adaptive risk assessment into LLM-based reasoning, improving prediction accuracy and risk management.

Contribution

It introduces a novel multi-agent system that combines behavioral insights and expert-guided retrieval to improve financial reasoning and decision-making with LLMs.

Findings

Outperforms baseline models in trend prediction accuracy.

Achieves higher risk-adjusted returns in trading tasks.

Enhances interpretability and robustness of financial predictions.

Abstract

Financial decision-making presents unique challenges for language models, demanding temporal reasoning, adaptive risk assessment, and responsiveness to dynamic events. While large language models (LLMs) show strong general reasoning capabilities, they often fail to capture behavioral patterns central to human financial decisions-such as expert reliance under information asymmetry, loss-averse sensitivity, and feedback-driven temporal adjustment. We propose FinHEAR, a multi-agent framework for Human Expertise and Adaptive Risk-aware reasoning. FinHEAR orchestrates specialized LLM-based agents to analyze historical trends, interpret current events, and retrieve expert-informed precedents within an event-centric pipeline. Grounded in behavioral economics, it incorporates expert-guided retrieval, confidence-adjusted position sizing, and outcome-based refinement to enhance interpretability and robustness. Empirical results on curated financial datasets show that FinHEAR consistently outperforms strong baselines across trend prediction and trading tasks, achieving higher accuracy and better risk-adjusted returns.