Agent Memory with Episodic Retrieval for Financial Decision-Making

2026-09-23

AI Summary

This study addresses the limitations of existing large language model-based trading agents, which lack state memory and struggle with complex, short-horizon market decisions. To this end, we propose META, a novel multi-agent architecture that integrates retrieval-augmented generation (RAG) with episodic memory. The framework combines multiple technical indicator agents with an episodic memory module, enabling market-state-aware adaptive signal reweighting through the retrieval of historical trading experiences. Experimental results demonstrate that the proposed approach significantly improves both the accuracy and robustness of short-term trading direction prediction. The source code is publicly available.

Abstract

Large language models (LLMs) have demonstrated strong capabilities in financial analysis and reasoning, inspiring recent advances in agent-based trading frameworks. While these systems show promise, prior approaches either emphasize long-horizon forecasting or operate as stateless analyzers, limiting their applicability to the demands of trading in complicated settings. To address these gaps, we introduce META (Memory Enhanced Trading Agent), the first RAG-like episodic-memory-augmented multi-agent framework for financial decision making. META integrates a family of specialized indicator agents (e.g., Trend, MACD, Stochastic, RSI, SMA, AVWAP, Heikin-Ashi) with a Decision Agent that fuses their reports, and a Memory module that retrieves and updates past trading episodes encoded as market state embeddings with outcomes and reflections. By recalling relevant experiences and adaptively reweighting signals under similar market regimes, META achieves improved directional accuracy and robustness under short-horizon evaluation. Our results demonstrate that episodic memory provides a powerful mechanism for regime-aware, interpretable, and low-latency decision-making in trading and decision making. The code of this project is released on GitHub.

Problem

• Financial Decision-Making
• Agent Memory
• Episodic Retrieval
• Trading Agent
• Large Language Models

Innovation

• Episodic Memory
• Multi-Agent Framework
• Retrieval-Augmented Generation
• Financial Decision-Making
• Regime-Aware