The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
FinMem: A Performance-Enhanced LLM Trading Agent With Layered Memory and Character Design
Abstract
We introduceFinMem, a novel Large Language Models (LLM)-based agent framework for financial trading, designed to address the need for automated systems that can transform real-time data into executable decisions.FinMemcomprises three core modules: Profile for customizing agent characteristics, Memory for hierarchical financial data assimilation, and Decision-making for converting insights into investment choices. The Memory module, which mimics human traders' cognitive structure, offers interpretability and real-time tuning while handling the critical timing of various information types. It employs a layered approach to process and prioritize data based on its timeliness and relevance, ensuring that the most recent and impactful information is given appropriate weight in decision-making.FinMem's adjustable cognitive span allows retention of critical information beyond human limits, enabling it to balance historical patterns with current market dynamics. This framework facilitates self-evolution of professional knowledge, agile reactions to investment cues, and continuous refinement of trading decisions in financial environments. When compared against advanced algorithmic agents using a large-scale real-world financial dataset,FinMemdemonstrates superior performance across classic metrics like Cumulative Return and Sharpe ratio. Further tuning of the agent's perceptual span and character setting enhances its trading performance, positioningFinMemas a cutting-edge solution for automated trading.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
The magical number seven, plus or minus two: Some limits on our capacity for processing information.
Miller, G. A. (1956) · Psychological Review · doi:10.1037/h0043158 · Cited by 17,812 · cited 1×
“Cognitive research suggests that human working memory is limited to recalling five to nine events at once (Miller 1956).”
BackgroundLevels of processing: A framework for memory research
Craik, F. I. M., & Lockhart, R. S. (1972) · Journal of Verbal Learning and Verbal Behavior · doi:10.1016/s0022-5371(72)80001-x · Cited by 9,566
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jégou, H. (2017) · arXiv · doi:10.48550/arxiv.1702.08734 · Cited by 4,140
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.00352 · Cited by 2,825
Sharpe, W. F. (1994) · The Journal of Portfolio Management · doi:10.3905/jpm.1994.409501 · Cited by 2,534
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173
Research works printed but not linked: 6
- Chen, 2012, Forecasting the Taiwan stock market with a novel momentum-based fuzzy time-series, Rev. Econ. Finance, 2, 38
- 10.1145/3586183.3606763 · DOI · Paper page
- 10.1145/3490354.3494366 · DOI
- Chung, 2013, Playing atari with deep reinforcement learning, Comput. Ence, 21
- Hull, 2007, Risk Management and Financial Institutions
- Raffin, 2021, Stable-baselines3: Reliable reinforcement learning implementations, 22, 1
Cited by
Capable language models can outgrow the benefits of collaboration
Kim, Y., Gu, K., Park, C., Park, C., Schmidgall, S., Heydari, A. A., Yan, Y., Zhang, Z., Zhuang, Y., Liu, Y., et al. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01268-y · Cited by 27
“Independent architecture’s universal underperformance (mean success 0.370 versus 0.466 SAS) stems from the absence of interagent 9 and 10, not by this table alone.”
InfluentialMem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Chhikara, P., Khant, D., Aryan, S., Singh, T., & Yadav, D. (2025) · arXiv · doi:10.48550/arxiv.2504.19413 · Cited by 10
TradingAgents: Multi-Agents LLM Financial Trading Framework
Xiao, Y., Sun, E., Luo, D., & Wang, W. (2024) · arXiv · doi:10.48550/arxiv.2412.20138 · Cited by 6
Empowered stock market forecasting using Large Language Model on social media content
Sperlí, G., & Sichinolfi, M. A. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112727 · Cited by 9
Toward Sustainable Agentic AI Systems: A Survey of Architectures and Methodologies
Lee, Y., & Park, E. (2026) · Sustainable Development · doi:10.1002/sd.70942 · Cited by 13
Large Language Models for Explainable Medical Text Summarization: A Systematic Literature Review
Ayalew, A. M., Hasan, M. R., Seppänen, T., & Oussalah, M. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70089 · Cited by 5
The Hitchhiker’s Guide to Autonomous Research: A Survey of Scientific Agents
Wang, X., Xu, J., Lian, S., Chen, Y., Guo, H., Zhu, F., Shao, Y., Ren, M., Yi, H., Feng, A. H., et al. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3721500 · Cited by 12
“FINMEM [142] simulates human financial decision-making with a memory system that prioritizes hierarchical data, featuring both working and long-term memory for time-sensitive insights.”
Can AI match professional analysts? Evidence from a multi-agent system
Francis, A., & Zhang, C. X. (2026) · Finance research letters · doi:10.1016/j.frl.2026.110127 · Cited by 1
Can AI Match Professional Analysts? Evidence from a Multi-Agent SystemPreprint
Francis, A., & Zhang, C. X. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5584131
Shen, Y., Zhang, Y., & Yuan, D. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3643296
“For example, a trader might need an LLM for both financial analyzes [12] and stock trading [13] simultaneously.”
SIFT: Scene-Imagination-Based Feature Reweighting
Qiu, J. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00298
Van, D. H., Karim, M. M., & Qu, Q. (2026) · AI · doi:10.3390/ai7040117
FinLumen: A Game-Theoretic Multi-Agent Framework for Rational Portfolio Management
Zhang, Z., Sen, P., Gu, F., Wang, H., Jiang, Z., & Su, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462217
Ayatollahi, M., & Jafari, S. M. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01072-y
“Similarly, FINMEM’s layered memory architecture [11] demonstrates how temporal specialization—separating immediate execution logic from longer-term strategy adaptation—enables both rapid response and continuous learning.”
Event-Driven Financial Market Analyses Using a Multi-Agent Framework
Chen, Q., & Madisetti, V. K. (2026) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2026.3688995
“Contemporary implementations of AI agents, exemplified by FinCon [8] for portfolio management, FinRobot [9] and FinAgent [10] for trading, and FinMem [11] for financial decision-making, reflect the increasing reliance on these technologies to execute complex financial tasks.”
Large language model-based multi-agent systems for financial markets simulation: a survey
Liu, Q., Yao, L., Wang, Z., Yang, Y., Tang, Y. J., Cheng, D., & Jiang, C. (2026) · Science China Information Sciences · doi:10.1007/s11432-026-4986-x · Cited by 3
“For example, FINMEM models human cognition using hierarchical memory to balance short-term signals with long-term strategy [110].”
Zhao, B., Li, Q., Wang, Z., Wang, Y., Cheng, P., & Lin, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31404-8_2 · Cited by 1
Consensus-Gated Execution: A Multi-Agent LLM Architecture for Autonomous Cryptocurrency Trading
Bajgora, A., Kulakov, A., & Merovcı, F. (2026) · Electronics · doi:10.3390/electronics15153453 · Cited by 1
Lifting the Veil of Non-Stationarity in Financial Market
Fu, V., Xu, X., Zhang, X., Xu, W., Ren, R., Deng, B., Zhao, X., Cao, J. W., & Cao, X. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817881
“(2) DL&RL-based methods: LSTM [12], LGBM [15], Transformer [37], PPO [30], SAC, DQN. and (3) LLM based methods: FinGPT [39], FinMem [41], FinAgent [45], Fin-Vision [10] and FinCon[42].”
Ddg: Domain-Knowledge Distilled Dual-Gating for Event-Driven Stock Prediction
Gou, T., Sun, Z. C., Sun, J., Wang, H., Wang, Y., & Zhang, B. (2026) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/hpsc69479.2026.00026
“Graph-based predictors further incorporate such structures into stock forecasting, from concept-level information sharing to multi-relational dynamic graphs [49], [57], while finance-oriented large models improve text representation and reasoning [55], [56], [59].”
Hsiao, I.-C., Tai, W.-S., & Liu, K.-H. (2026) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan71481.2026.11652699
“Recent LLM-based trading agents incorporate these technical signals into end-to-end decision loops, showing promising performance and agentic autonomy [1, 2].”
Fin-DR: Learning DeepResearch Agent for Financial Time-Series ForecastingPreprint
Duan, J., Zhang, Y., Junfu, Z., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7422697
TextGrad-Trader: Risk-Aware Multimodal Signal Arbitration for Adaptive Stock Prediction ServicesPreprint
Wu, T., Gong, W., Wang, D., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7455222
A Brief Survey of LLMs and Intelligent Agents in Financial Investment Decision Making
He, Z., Li, M., & Zhang, Y. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.08.177
Feng, X., Cardozo, J. P., & Xia, D. (2026) · Journal of Economic Surveys · doi:10.1111/joes.70178 · Cited by 1
Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance
Benhenda, M. (2026) · arXiv
Metadata
- Authors
- Yu, Y., Li, H., Chen, Z., Jiang, Y., Li, Y., Suchow, J. W., Zhang, D., & Khashanah, K.
- Affiliations
- Stevens Institute of Technology (US)
- ORCID
- Venue
- IEEE Transactions on Big Data
- Published
- 2025-12
- Volume
- 11
- Issue
- 6
- Pages
- 3443-3459
- ISSN
- 2332-7790 (ISSN-L)
- 2372-2096
- OpenAlex
- W4412939561
- Cited by
- 23
- References
- 50
- Citations by year
- 2026: 20 · 2025: 3
- FWCI
- 17.60
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Big Data (publishedVersion)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Social Sciences › Business, Management and Accounting › Management Information Systems › FinTech, Crowdfunding, Digital Finance
- Keywords
- algorithmic trading, financial trading, real-time data processing, investment decision-making, interpretability, Sharpe ratio, cumulative returns
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.