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
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Self-citationA survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · cited 1×
“This approach, when reinforced with well-designed prompt templates, markedly improves decision-making in various sectors (Wang et al. 2023).”
BackgroundSelf-citationA Survey on Large Language Model based Autonomous Agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.11432 · Cited by 1,925
Self-citationThe Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
Ethayarajh, K. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1006 · Cited by 841 · cited 1×
“Its cognitive load can be flexibly adjusted by tuning the number of retrieved events from each layer of long-term memory, allowing F IN M EM to deliver superior trading decisions in data-rich contexts.”
BackgroundCognitive Architectures for Language Agents
Sumers, T. R., Yao, S., Narasimhan, K., & Griffiths, T. L. (2023) · arXiv · doi:10.48550/arxiv.2309.02427 · Cited by 798
Replication and Analysis of Ebbinghaus’ Forgetting Curve
Murre, J. M. J., & Dros, J. (2015) · PLOS ONE · doi:10.1371/journal.pone.0120644 · Cited by 777
Proximal Policy Optimization in StarCraft
Liu, Y. (2025) · doi:10.12794/metadc1505267 · Cited by 615
Black, F. (1986) · The Journal of Finance · doi:10.2307/2328481 · Cited by 599
FinGPT: Open-Source Financial Large Language Models
Yang, H., Liu, X.-Y., & Wang, C. D. (2023) · doi:10.2139/ssrn.4489826 · Cited by 475
A Survey of Large Language Models for Financial Applications: Progress, Prospects and ChallengesPreprint
Nie, Y., Kong, Y., Dong, X., Mulvey, J. M., Poor, H. V., Wen, Q., & Zohren, S. (2024) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2406.11903 · Cited by 398
BloombergGPT: A Large Language Model for Finance
Wu, S., Irsoy, O., Lu, S., Dabravolski, V., Dredze, M., Gehrmann, S., Kambadur, P., Rosenberg, D., & Mann, G. (2023) · arXiv · Cited by 357
FinGPT: Open-Source Financial Large Language Models
Yang, H., Liu, X.-Y., & Wang, C. D. (2023) · arXiv · doi:10.48550/arxiv.2306.06031 · Cited by 326
Large Language Models in Finance: A Survey
Li, Y., Wang, S., Ding, H., & Chen, H. (2023) · 4th ACM International Conference on AI in Finance · doi:10.1145/3604237.3626869 · Cited by 274
Self-citationTechnical Analysis of Stock Trends
Edwards, R. D., Magee, J., & Bassetti, W. H. C. (2018) · CRC Press eBooks · doi:10.4324/9781315115719 · Cited by 265
Sonkavde, G., Dharrao, D. S., Bongale, A. M., Deokate, S. T., Doreswamy, D., & Bhat, S. K. (2023) · International Journal of Financial Studies · doi:10.3390/ijfs11030094 · Cited by 262
Social Simulacra: Creating Populated Prototypes for Social Computing Systems
Park, J. S., Popowski, L., Cai, C., Morris, M. R., Liang, P., & Bernstein, M. S. (2022) · Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3526113.3545616 · Cited by 212
Deep reinforcement learning for automated stock trading: an ensemble strategy
Yang, H., Liu, X.-Y., Zhong, S., & Walid, A. (2020) · Proceedings of the First ACM International Conference on AI in Finance · doi:10.1145/3383455.3422540 · Cited by 196 · cited 1×
“Experiments show that F IN M EM evolves its knowledge base from past trades and ongoing market interactions, maintaining robustness in complex environments.”
BackgroundDesiderata for cognitive architectures
Sun, R. (2004) · Philosophical Psychology · doi:10.1080/0951508042000286721 · Cited by 193 · cited 2×
“These shortfalls affect their daily knowledge updating capability, due to a lack of a memory component, thereby diminishing their effectiveness in prioritizing critical events.”
BackgroundAutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.08155 · Cited by 193
Human cognitive architecture: Why some instructional procedures work and others do not.
Sweller, J. (2012) · APA educational psychology handbook, Vol 1: Theories, constructs, and critical issues. · doi:10.1037/13273-011 · Cited by 184 · cited 1×
“F IN M EM ’s memory module can mirror the human cognitive system (Sweller 2012) and facilitate agile, real-time decisions (Sun 2004).”
BackgroundFinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language ModelsPreprint
Yang, H., Zhang, B., Wang, N., Guo, C., Zhang, X., Lin, L., Wang, J., Zhou, T., Guan, M., Zhang, R., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4841493 · Cited by 184
AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
Qiao, S., Zhang, N., Fang, R., Luo, Y., Zhou, W., Jiang, Y., Lv, C., & Chen, H. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.165 · Cited by 177
Self-citationVolatility tests and efficient markets
Cochrane, J. H. (1991) · Journal of Monetary Economics · doi:10.1016/0304-3932(91)90018-j · Cited by 166
Huang, B., Huan, Y., Xu, L. D., Zheng, L., & Zou, Z. (2018) · Enterprise Information Systems · doi:10.1080/17517575.2018.1493145 · Cited by 140 · cited 1×
“The development of autonomous trading systems has progressed from initial rule-based strategies (Edwards, Magee, and Bassetti 2018) to advanced machine-learning algorithms (Huang et al. 2019).”
BackgroundDeep Reinforcement Learning in Quantitative Algorithmic Trading: A ReviewPreprint
Pricope, T.-V. (2021) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2106.00123 · Cited by 104
Naveed, M., Ali, S., Iqbal, K., & Sohail, M. K. (2020) · South Asian Journal of Business Studies · doi:10.1108/sajbs-09-2019-0168 · Cited by 90
Liu, X.-Y., Yang, H., Gao, J., & Wang, C. D. (2021) · Proceedings of the Second ACM International Conference on AI in Finance · doi:10.1145/3490354.3494366 · Cited by 87
Aharon, D. Y., Ali, S., & Naved, M. (2023) · Research in International Business and Finance · doi:10.1016/j.ribaf.2023.102036 · Cited by 82
Adaptive stock trading with dynamic asset allocation using reinforcement learning
Jangmin, O., Lee, J., Lee, J. W., & Zhang, B. (2005) · Information Sciences · doi:10.1016/j.ins.2005.10.009 · Cited by 81 · cited 1×
“F IN M EM ’s profiling module features dynamic character settings, enabling continuous updates in domain knowledge and risk preference to adapt to volatile trading environments, thereby enhancing F IN M EM ’s capabilities.”
BackgroundAli, S., Naveed, M., Hanif, H., & Gubareva, M. (2023) · International Review of Financial Analysis · doi:10.1016/j.irfa.2023.103045 · Cited by 77
Deep Reinforcement Learning for Trading—A Critical Survey
Millea, A. (2021) · Data · doi:10.3390/data6110119 · Cited by 74
A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
Zhang, W., Zhao, L., Xia, H., Sun, S., Sun, J., Qin, M., Li, X., Zhao, Y., Zhao, Y., Cai, X., et al. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671801 · Cited by 74
A survey on deep reinforcement learning architectures, applications and emerging trends
Balhara, S., Gupta, N., Alkhayyat, A. H., Bharti, I., Malik, R. Q., Mahmood, S. N., & Abedi, F. (2022) · IET Communications · doi:10.1049/cmu2.12447 · Cited by 73 · cited 2×
“While this avoids information overload, it may lead to insufficient insight for accurate decision-making.”
BackgroundMaking Language Models Better Reasoners with Step-Aware Verifier
Li, Y., Lin, Z., Zhang, S., Fu, Q., Chen, B., Lou, J.-G., & Chen, W. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.291 · Cited by 69 · cited 1×
“These shortfalls affect their daily knowledge updating capability, due to a lack of a memory component, thereby diminishing their effectiveness in prioritizing critical events.”
BackgroundSelf-citationDeep reinforcement learning for financial trading using multi-modal features
Avramelou, L., Nousi, P., Passalis, N., & Tefas, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121849 · Cited by 58 · cited 1×
“Its cognitive load can be flexibly adjusted by tuning the number of retrieved events from each layer of long-term memory, allowing F IN M EM to deliver superior trading decisions in data-rich contexts.”
BackgroundPätäri, E. J., & Vilska, M. (2014) · Applied Economics · doi:10.1080/00036846.2014.914145 · Cited by 57 · cited 1×
“In its agent memory module design, F IN M EM emulates human working and layered long-term memory mechanisms.”
BackgroundReinforcement Learning in Stock Trading
Dang, Q.-V. (2020) · Advances in Intelligent Systems and Computing · doi:10.1007/978-3-030-38364-0_28 · Cited by 57 · cited 1×
“F IN M EM ’s profiling module features dynamic character settings, enabling continuous updates in domain knowledge and risk preference to adapt to volatile trading environments, thereby enhancing F IN M EM ’s capabilities.”
BackgroundStock trading rule discovery with double deep Q-network
Shi, Y., Li, W., Zhu, L., Guo, K., & Cambria, E. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107320 · Cited by 57 · cited 1×
“Experiments show that F IN M EM evolves its knowledge base from past trades and ongoing market interactions, maintaining robustness in complex environments.”
BackgroundSentiment-influenced trading system based on multimodal deep reinforcement learning
Chen, Y., & Huang, S.-H. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107788 · Cited by 55 · cited 1×
“Its cognitive load can be flexibly adjusted by tuning the number of retrieved events from each layer of long-term memory, allowing F IN M EM to deliver superior trading decisions in data-rich contexts.”
BackgroundFinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement LearningPreprint
Liu, X.-Y. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4253139 · Cited by 48
Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
Li, J., Lai, Y., Li, W., Ren, J., Zhang, M., Kang, X., Wang, S., Li, P., Zhang, Y.-Q., Ma, W., et al. (2024) · arXiv · doi:10.48550/arxiv.2405.02957 · Cited by 46
Naveed, M., Ali, S., Gubareva, M., & Omri, A. (2023) · Research in International Business and Finance · doi:10.1016/j.ribaf.2023.102160 · Cited by 44
Lob-based deep learning models for stock price trend prediction: a benchmark study
Prata, M., Masi, G., Berti, L., Arrigoni, V., Coletta, A., Cannistraci, I., Vyetrenko, S. S., Velardi, P., & Bartolini, N. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-024-10715-4 · Cited by 44
The neurobiology of deep reinforcement learning
Gershman, S. J., & Ölveczky, B. P. (2020) · Current Biology · doi:10.1016/j.cub.2020.04.021 · Cited by 28 · cited 2×
“Secondly, integrating textual data with numerical features, crucial in finance, poses a challenge for DRL agents on convergence (Gershman and ¨Olveczky 2020).”
BackgroundNexus between bank capital and risk-taking behaviour: Empirical evidence from US commercial banks
Abbas, F., Ali, S., Moudud‐Ul‐Huq, S., & Naveed, M. (2021) · Cogent Business & Management · doi:10.1080/23311975.2021.1947557 · Cited by 28
Zhang, P., Shi, X., & Khan, S. U. (2018) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2018.2847629 · Cited by 23
Ali, S., Naveed, M., SALEEM, A., et al. (2022) · Annals of Financial Economics · doi:10.1142/s2010495222500269 · Cited by 20
Vaidya, R. (2020) · Quantitative Economics and Management Studies · doi:10.35877/454ri.qems197 · Cited by 18 · cited 1×
“In its agent memory module design, F IN M EM emulates human working and layered long-term memory mechanisms.”
BackgroundFarah, M. F., Naveed, M., & Ali, S. (2023) · Springer proceedings in business and economics · doi:10.1007/978-3-031-32894-7_5 · Cited by 13
Downside RiskPreprint
Ang, A., Chen, J. S., & Xing, Y. (2004) · SSRN Electronic Journal · doi:10.2139/ssrn.641843 · Cited by 6
PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance
Xie, Q., Han, W., Zhang, X., Lai, Y., Peng, M., Lopez-Lira, A., & Huang, J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1454
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 13
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
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.