Athenarabeta

athenara:~$ registry cite papers/finmem-paper

FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Proposes an LLM trading agent whose layered memory and configurable character profile let it adapt to new market information over multiple time horizons.

RepositoryarXiv:2311.13743MarkdownEdit this entry

#llm-agent #memory #cognitive-architecture #profiling

added 2026-08-15 · external

$ git clone https://github.com/pipiku915/FinMem-LLM-StockTrading
@article{finmem-paper,
  title         = {FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design},
  author        = {Yangyang Yu and Haohang Li and Zhi Chen and Yuechen Jiang and Yang Li and Denghui Zhang and Rong Liu and Jordan W. Suchow and Khaldoun Khashanah},
  year          = {2023},
  eprint        = {2311.13743},
  archiveprefix = {arXiv},
  note          = {ICLR 2024 Workshop on LLM Agents},
}

Presents a three-module agent architecture combining profiling, layered memory processing that imitates human trader cognition, and decision-making. The design lets the agent self-evolve its domain knowledge, react to new investment cues, and refine trading decisions over time.

Experiments on real-world financial data report performance above algorithmic baselines, with results varying by the agent’s cognitive span and personality configuration — an early demonstration that memory design, not just model choice, moves trading performance.

(END)

trading [●●···] basic   ai [●●●··] moderate   programming [●····] none   setup [●····] none

origin external
markets equities

describes FinMem

extended by Can LLM-based Financial Investing Strategies Outperform the Market in Long Run? · FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making · From Deep Learning to LLMs: A Survey of AI in Quantitative Investment · InvestorBench

athenara:~$