Paper: arXiv 2309.03736
Authors: Yang Li, Yangyang Yu, Haohang Li, Zhi Chen, Khaldoun Khashanah
Abstract
Large Language Models (LLMs), prominently highlighted by the recent evolution in the Generative Pre-trained Transformers (GPT) series, have displayed significant prowess across various domains, such as aiding in healthcare diagnostics and curating analytical business reports. The efficacy of GPTs lies in their ability to decode human instructions, achieved through comprehensively processing historical inputs as an entirety within their memory system. Yet, the memory processing of GPTs does not precisely emulate the hierarchical nature of human memory. This can result in LLMs struggling to prioritize immediate and critical tasks efficiently. To bridge this gap, we introduce an innovative LLM multi-agent framework endowed with layered memories. We assert that this framework is well-suited for stock and fund trading, where the extraction of highly relevant insights from hierarchical financial data is imperative to inform trading decisions. Within this framework, one agent organizes memory into three distinct layers, each governed by a custom decay mechanism, aligning more closely with human cognitive processes. Agents can also engage in inter-agent debate. In financial trading contexts, LLMs serve as the decision core for trading agents, leveraging their layered memory system to integrate multi-source historical actions and market insights. This equips them to navigate financial changes, formulate strategies, and debate with peer agents about investment decisions. Another standout feature of our approach is to equip agents with individualized trading traits, enhancing memory diversity and decision robustness. These sophisticated designs boost the system’s responsiveness to historical trades and real-time market signals, ensuring superior automated trading accuracy.
Complexity vs Empirical Score
- Math Complexity: 1.5/10
- Empirical Rigor: 6.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper introduces a novel LLM multi-agent architecture with layered memory and distinct characters, but the mathematics is limited to conceptual definitions rather than dense formulas or derivations. It demonstrates high empirical rigor through the description of a comprehensive data warehouse, specific API integration (Databento, Alpaca, OpenAI), vector database usage (FAISS), and a planned backtest against ARK fund records.
Research Flowchart
flowchart TD A["Research Goal: Enhance LLMs for Financial Trading"] --> B["Methodology: Multi-Agent System with Layered Memory"] B --> C["Inputs: Historical Market Data & Trading Actions"] C --> D["Layered Memory Processing with Custom Decay"] D --> E["Inter-Agent Decision Debate"] E --> F["Output: Formulated Trading Strategies"] F --> G["Outcome: Improved Trading Accuracy & Performance"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes TradingGPT, an LLM-powered multi‑agent trading framework with layered memories and individualized trading characters.
Source sentence
We introduce an innovative LLM multi-agent framework endowed with layered memories.
Assumes
No explicit assumptions found in the text.
Data
- Databento Stock Price Database market-prices unknown
Source sentence
These datasets were sourced from financial databases and APIs, exemplified by the Databento Stock Price Database, Alpaca News API, publicly available daily holdings history records from ARK, etc.
- Alpaca News API text-news unknown
Source sentence
These datasets were sourced from financial databases and APIs, exemplified by the Databento Stock Price Database, Alpaca News API, publicly available daily holdings history records from ARK, etc.
- ARK funds historical trading records fundamentals unknown
Source sentence
These datasets were sourced from financial databases and APIs, exemplified by the Databento Stock Price Database, Alpaca News API, publicly available daily holdings history records from ARK, etc.
- Audio transcriptions from ARK Invest videos alternative unknown
Source sentence
The majority of our data, including audio transcriptions from ARK Invest videos (translated to texts via the Whisper API), benefits from FAISS’s unique underlying structure to fast query data.
Costs
Unclear
Finds
No quantified findings extracted.
Checked by others
No other paper in the archive has been found to support or contradict these findings. Coverage is partial, so this is neither replication nor refutation.
24 papers in the archive
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.