Paper: arXiv 2411.04788
Authors: Xuewen Han, Neng Wang, Shangkun Che, Hongyang Yang, Kunpeng Zhang, Sean Xin Xu
Abstract
In recent years, the application of generative artificial intelligence (GenAI) in financial analysis and investment decision-making has gained significant attention. However, most existing approaches rely on single-agent systems, which fail to fully utilize the collaborative potential of multiple AI agents. In this paper, we propose a novel multi-agent collaboration system designed to enhance decision-making in financial investment research. The system incorporates agent groups with both configurable group sizes and collaboration structures to leverage the strengths of each agent group type. By utilizing a sub-optimal combination strategy, the system dynamically adapts to varying market conditions and investment scenarios, optimizing performance across different tasks. We focus on three sub-tasks: fundamentals, market sentiment, and risk analysis, by analyzing the 2023 SEC 10-K forms of 30 companies listed on the Dow Jones Index. Our findings reveal significant performance variations based on the configurations of AI agents for different tasks. The results demonstrate that our multi-agent collaboration system outperforms traditional single-agent models, offering improved accuracy, efficiency, and adaptability in complex financial environments. This study highlights the potential of multi-agent systems in transforming financial analysis and investment decision-making by integrating diverse analytical perspectives.
Complexity vs Empirical Score
- Math Complexity: 2.5/10
- Empirical Rigor: 6.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper focuses on practical AI agent implementation and testing on real SEC 10-K data, with empirical results like prediction accuracy metrics, but contains minimal advanced mathematical formalism or derivations.
Research Flowchart
flowchart TD
A["Research Goal: Enhance Investment Analysis<br>by Optimizing AI-Agent Collaboration"] --> B{"Data Collection & Selection"}
B --> C["Input: 30 Dow Jones 10-K Forms (2023)"]
C --> D["Multi-Agent Collaboration System"]
D --> E{"Sub-Optimal Combination Strategy"}
E --> F["Computational Task Groups"]
F --> G["Fundamentals Analysis"]
F --> H["Market Sentiment Analysis"]
F --> I["Risk Analysis"]
G --> J{"Dynamic Adaptation to Market Conditions"}
H --> J
I --> J
J --> K["Outcomes: Multi-Agent System Outperforms Single-Agent Models"]
K --> L["Key Findings:<br>1. Improved Accuracy<br>2. Enhanced Efficiency<br>3. Greater Adaptability"]
style A fill:#e1f5e1
style K fill:#f0e1ff
style L fill:#fff2cc
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 a novel multi-agent collaboration system to enhance financial investment research decision‑making.
Source sentence
we propose a novel multi-agent collaboration system designed to enhance decision-making in financial investment research.
Assumes 1
- Searches for stock movements or social media are limited to before the report release to avoid data leakage. data
Source sentence
all the search ranges of either stock movements or social media are limited to before the release date of the report to prevent data leakage.
Data
- 2023 SEC 10‑K forms text-news public
Source sentence
We focus on three sub-tasks: fundamentals, market sentiment, and risk analysis, by analyzing the 2023 SEC 10‑K forms of 30 companies listed on the Dow Jones Index.
- Stock prices at report release and one week later market-prices public
Source sentence
The data set used for investment research includes the 2023 annual reports of the 30 Dow Jones Index companies, along with stock prices at the time of report release and one week later.
Costs
Not applicable
Finds 3
- The ensemble agent structure achieved the highest binary prediction accuracy of 66.7%, outperforming the vertical structure's 50%. performance
Source sentence
the ensemble structure successfully predicted the movements of 20 stocks, achieving a prediction accuracy of 66.7%, whereas the full vertical agent structure only achieved 50%.
- Dual‑agent structures yielded the smallest target price difference, though ensemble agents still outperformed in overall accuracy. performance
Source sentence
Despite the smallest target price difference is observed in dual agent structures, the ensemble agent structure outperforms other structures in price prediction accuracy.
- The multi‑agent collaboration system outperformed traditional single‑agent models in accuracy, efficiency, and adaptability. performance
Source sentence
The results demonstrate that our multi-agent collaboration system outperforms traditional single-agent models, offering improved accuracy, efficiency, and adaptability in complex financial environments.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 10 related papers). Coverage is partial, so this is neither replication nor refutation.
6 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.
Cited References (134)
- The patent holder’s dilemma: Buy, sell, or troll? (2007) — link
- Deciding equivalances among conjunctive aggregate queries (2007) — link
- Special issue: Digital Libraries (1996)
- Understanding Policy-Based Networking (2001)
- First-Order Dynamic Logic (1979) — link
- The title of book one (2007) — link
- The title of book two (2008) — link
- Achieving application requirements (1990) — link
and 126 more
- Statecarts in use: structured analysis and object-orientation (1998) — link
- The Art of Computer Programming, Vol. 1: Fundamental Algorithms (3rd. ed.) (1997)
- The Art of Computer Programming (1998)
- An experiment in bibliographic mark-up: Parsing metadata for XML export (2010) — link
- Catch me, if you can: Evading network signatures with web-based polymorphic worms (2007)
- Catch me, if you can: Evading network signatures with web-based polymorphic worms (2008)
- Catch me, if you can: Evading network signatures with web-based polymorphic worms (2009)
- Predicate Path expressions (1979) — link
- LOGICS of Programs: AXIOMATICS and DESCRIPTIVE POWER (1978)
- Optimal Motion Control of a Ground Vehicle (2003)
- Algorithms for Closest-Point Problems (Computational Geometry) (1985)
- Introduction to Bayesian Statistics (2001) — link
- CLIFFORD: a Maple 11 Package for Clifford Algebra Computations, version 11 (2007) — link
- Stats and Analysis (2006) — link
- A more perfect union (2008) — link
- The fountain of youth (2009)
- Solder man (2003) — link
- Interview with Bill Kinder: January 13, 2005 (2005) — link
- The Enabling of Digital Libraries (2008)
- (old) Finding minimum congestion spanning trees (2000) — link
- (new) Finding minimum congestion spanning trees (2000) — link
- (old) Distributed data source verification in wireless sensor networks (2009) — link
- (new) Distributed data source verification in wireless sensor networks (2009) — link
- Portalis: using competitive online interactions to support aid initiatives for the homeless (2008) — link
- Visual Basic 6: Design, Specification, and Objects with Other (1999)
- The Latex Web Companion: Integrating TEX, HTML, and XML (1999)
- Vertex Types in Book-Embeddings (1987)
- Vertex Types in Book-Embeddings (1987)
- CHI ‘08: CHI ‘08 extended abstracts on Human factors in computing systems (2008)
- Algorithms for Closest-Point Problems (Computational Geometry) (1985)
- IEEE TCSC Executive Committee (2004) — link
- Distributed systems (2nd Ed.) (1993)
- New Algorithms for Dependency-Directed Backtracking (Master’s thesis) (1986)
- New Algorithms for Dependency-Directed Backtracking (Master’s thesis) (1986)
- Seminumerical Algorithms (1981)
- E-commerce and cultural values (2001) — link
- Chapter 9 (2002) — link
- The implementation of electronic commerce in SMEs in Singapore (Incoll) (2003) — link
- E-commerce and cultural values - (InBook-num-in-chap) (2004) — link
- E-commerce and cultural values (Inbook-text-in-chap) (2005) — link
- E-commerce and cultural values (Inbook-num chap) (2006) — link
- A library-based synthesis methodology for reversible logic (2010)
- Synthesis of Reversible Circuit Using Cycle-Based Approach (2010)
- Algorithmic Enumeration of Ideal Classes for Quaternion Orders (2010) — link
- Chapter II: Notes on data structuring (1972) — link
- Transcript of question and answer session (1981) — link
- Go to statement considered harmful (1979) — link
- Three-dimensional virtual acoustic displays (1992) — link
- Managerial expert systems and organizational change: some critical research issues (1987) — link
- Simplified Structured COBOL with Microsoft/MicroFocus COBOL (1990)
- A multi-radio unification protocol for IEEE 802.11 wireless networks (2004)
- Wireless Sensor Networks: A Survey (2002)
- A Survey on Wireless Multimedia Sensor Networks (2007)
- SSCH : Slotted Seeded Channel Hopping for Capacity Improvement in IEEE 802.11 Ad-Hoc Wireless Networks (2004)
- XBOW Sensor Motes Specifications (2008)
- Overview of Sensor Networks (2004)
- CodeBlue : Sensor Networks for Medical Care (2008)
- Investigating Network Architectures for Body Sensor Networks (2007)
- Channel-Hopping Multiple Access (2000)
- Body Sensor Networks (2008)
- Mapping Powerlists onto Hypercubes (1994)
- Automatic Parallelization for Distributed-Memory Multiprocessing Systems (1989)
- User recovery and reversal in interactive systems (1984)
- Generalizing specifications for uniformly implemented loops (1985)
- Towards monolingual programming environments (1985)
- The \TeX book (1984)
- Distributed algorithms for finding centers and medians in networks (1984)
- \it \LaTeX : A Document Preparation System (1986)
- Program transformations in a denotational setting (1985)
- Seminumerical Algorithms (1981)
- A high-level approach to computer document formatting (1980)
- A multifrequency MAC specially designed for wireless sensor network applications (2010) — link
- Institutional members of the \TeX Users Group (2017) — link
- acmart— Class for typesetting publications of ACM (2017) — link
- The \textsl doclicense package (2022) — link
- Reasoning About Naming Systems (1993) — link
- Babel, a Multilingual Style-Option System for Use with LaTeX’s Standard Document Styles (1991)
- A Methodology for Implementing Highly Concurrent Data Objects (1993) — link
- Publication quality tables in \LaTeX (2005)
- Using the amsthm Package (2015)
- R: A Language and Environment for Statistical Computing (2019) — link
- UMass Citation Field Extraction Dataset (2013) — link
- Citation concept analysis (CCA) —A new form of citation analysis revealing the usefulness of concepts for other researchers illustrated by two exemplary case studies including classic books by Thomas S.~Kuhn and Karl R.~Popper (2019) — link
- Learning Soft Linear Constraints with Application to Citation Field Extraction (2014) — link
- Maintaining Discrete Probability Distributions Optimally (1993)
- When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments — → 2407.18957
- FinAgent: A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist — → 2402.18485
- Fundamental analysis, future earnings, and stock prices (1997)
- Twitter mood predicts the stock market (2011)
- The evaluation of risk in business investment (2014)
- The effect of financial reporting quality on corporate investment efficiency: Evidence from the Tunisian stock market (2017)
- Measure for measure: The relation between forecast accuracy and recommendation profitability of analysts (2007)
- Through the eyes of analysts: a content analysis of analyst report narratives’ (2004)
- Artificial Intelligence for Text Generation: An Intellectual Property Perspective (2023)
- Large language models for social networks: Applications, challenges, and solutions (2024) — link
- A survey of large language models (2023) — link
- Attention is all you need (2017)
- Bert: Pre-training of deep bidirectional transformers for language understanding (2018) — link
- Improving language understanding by generative pre-training (2018)
- GPT-3: Its nature, scope, limits, and consequences (2020)
- Language models are few-shot learners (2020)
- Generative agents: Interactive simulacra of human behavior (2023)
- Large language models for robotics: A survey (2023) — link
- The rise and potential of large language model based agents: A survey (2023) — link
- Agent ai: Surveying the horizons of multimodal interaction (2024) — link
- A survey on large language model based autonomous agents (2024)
- Personal llm agents: Insights and survey about the capability, efficiency and security (2024) — link
- AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments (2024) — link
- Describe, explain, plan and select: interactive planning with LLMs enables open-world multi-task agents (2024)
- A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges — → 2406.11903
- Financial statement analysis with large language models — → 2407.17866
- Bloomberggpt: A large language model for finance (2023) — link
- FinGPT: Open-Source Financial Large Language Models — → 2306.06031
- FinMem: A performance-enhanced LLM trading agent with layered memory and character design — → 2311.13743
- Can LLMs Answer Investment Banking Questions? Using Domain-Tuned Functions to Improve LLM Performance on Knowledge-Intensive Analytical Tasks (2024)
- Investlm: A large language model for investment using financial domain instruction tuning — → 2309.13064
- Revolutionizing finance with llms: An overview of applications and insights (2024) — link
- Can ChatGPT improve investment decisions? From a portfolio management perspective (2024)
- Improving factuality and reasoning in language models through multiagent debate (2023) — link
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019) — link
- Finnhub-Stock-API/finnhub-python (2024)
- FinancialModelingPrepAPI/Financial-Modeling-Prep-API (2023)
- praw-dev/praw (2024)
- ranaroussi/yfinance (2024)
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework (2024)
- FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models — → 2405.14767
8 of 134 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.