AI Agents in Financial Markets: Architecture, Applications, and Systemic Implications

Paper: arXiv 2603.13942

Authors: Hui Gong

Abstract

Recent advances in large language models, tool-using agents, and financial machine learning are shifting financial automation from isolated prediction tasks to integrated decision systems that can perceive information, reason over objectives, and generate or execute actions. This paper develops an integrative framework for analysing agentic finance: financial market environments in which autonomous or semi-autonomous AI systems participate in information processing, decision support, monitoring, and execution workflows. The analysis proceeds in three steps. First, the paper proposes a four-layer architecture of financial AI agents covering data perception, reasoning engines, strategy generation, and execution with control. Second, it introduces the Agentic Financial Market Model (AFMM), a stylised agent-based representation linking agent design parameters such as autonomy depth, heterogeneity, execution coupling, infrastructure concentration, and supervisory observability to market-level outcomes including efficiency, liquidity resilience, volatility, and systemic risk. Third, it presents an illustrative empirical application based on event studies of AI-agent capability disclosures and heterogeneous market repricing. The paper argues that the systemic implications of AI in finance depend less on model intelligence alone than on how agent architectures are distributed, coupled, and governed across institutions. The empirical application is intentionally exploratory: it does not validate the full AFMM, but shows how one observable expectations channel can be studied using public data. In the near term, the most plausible equilibrium is bounded autonomy, in which AI agents operate as supervised co-pilots, monitoring systems, and constrained execution modules embedded within human decision processes.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 4.5/10
• Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: The paper provides a timely and highly articulate conceptual framework for multi-agent LLM systems in market microstructures, supported by a stylised model and exploratory event study. However, it lacks deep theoretical mathematical proofs and rigorous, large-scale empirical backtesting.

Research Flowchart

  flowchart TD
    A["Research Goal: Analyze Systemic Implications of AI Agents in Financial Markets"] --> B["Step 1: Propose 4-Layer Agent Architecture<br/>(Perception, Reasoning, Strategy, Execution)"]
    
    B --> C["Step 2: Develop Agentic Financial Market Model (AFMM)<br/>(Links Agent Autonomy & Coupling to Market Risk)"]
    
    C --> D["Step 3: Empirical Event Study<br/>(Public Data on AI Capability Disclosures & Market Repricing)"]
    
    D --> E["Key Outcome 1: Systemic Risk Depends on Agent Architecture & Governance, Not Model Intelligence Alone"]
    
    D --> F["Key Outcome 2: Near-Term Equilibrium is Bounded Autonomy<br/>(AI as Supervised Co-Pilots & Constrained Modules)"]

Cited References (42)

1. BloombergGPT : A Large Language Model for Finance (2023) — link
2. FinGPT : Open-Source Financial Large Language Models — → 2306.06031
3. FinBen : A Holistic Financial Benchmark for Large Language Models (2024) — link
4. Fin-R1 : A Large Language Model for Financial Reasoning through Reinforcement Learning (2025) — link
5. ReAct : Synergizing Reasoning and Acting in Language Models (2023) — link
6. Generative Agents: Interactive Simulacra of Human Behavior (2023) — link
7. The Rise and Potential of Large Language Model Based Agents: A Survey (2023) — link
8. FinTeam : A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios (2025) — link

2 of 42 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.