Large Language Model Agent in Financial Trading: A Survey
On the map: LLM agents and tool use → Financial trading and forecasting agents
Abstract (arXiv)
Trading is a highly competitive task that requires a combination of strategy, knowledge, and psychological fortitude. With the recent success of large language models(LLMs), it is appealing to apply the emerging intelligence of LLM agents in this competitive arena and understanding if they can outperform professional traders. In this survey, we provide a comprehensive review of the current research on using LLMs as agents in financial trading. We summarize the common architecture used in the agent, the data inputs, and the performance of LLM trading agents in backtesting as well as the challenges presented in these research. This survey aims to provide insights into the current state of LLM-based financial trading agents and outline future research directions in this field.
Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 29 of its 59 references that are in the map. First posted on arXiv 26 Jul 2024.
Builds on
29 of 59 references.
Closest ancestors · 1
Same direction, newest first
Other references · 28
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2023GPT-4 Technical Reportcited by 18,132
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
- 2023Large Language Models in Finance: A Surveycited by 223
- 2024A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalistcited by 137
- 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 132
- 2023Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Modelscited by 125
16 more
- 2024Simulating Classroom Education with LLM-Empowered Agentscited by 125
- 2017A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problemcited by 123
- 2023Towards Mitigating Hallucination in Large Language Models via Self-Reflectioncited by 81
- 2024A Survey of Large Language Models in Finance (FinLLMs)cited by 77
- 2014Understanding Random Forests: From Theory to Practicecited by 57
- 2023Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investmentcited by 54
- 2023A Practical Survey on Zero-shot Prompt Design for In-context Learningcited by 49
- 2024Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Modelscited by 35
- 2024LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Predictioncited by 31
- 2024FinLlama: Financial Sentiment Classification for Algorithmic Trading Applicationscited by 22
- 2023Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Predictioncited by 16
- 2023Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?cited by 15
- 2024StockGPT: A GenAI Model for Stock Prediction and Tradingcited by 11
- 2024FinVerse: An Autonomous Agent System for Versatile Financial Analysiscited by 5
- 2022Evaluating Impact of Social Media Posts by Executives on Stock Pricescited by 2
- 2019A General Framework on Enhancing Portfolio Management with Reinforcement Learningcited by 1
Built on by
Citing papers per year: 2024: 3; 2025: 36; 2026: 21.
60 papers.
Sort:
By area:
- 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
- 2025Agentic Large Language Models, a surveycited by 105
- 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agentscited by 82
- 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutioncited by 65
- 2025Efficient Inference for Large Reasoning Models: A Surveycited by 58
- 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
- 2025FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoningcited by 26
- 2025Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Frameworkcited by 25
- 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 25
- 2025LLM-Powered AI Agent Systems and Their Applications in Industrycited by 22
- 2025Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?cited by 19
- 2025On the Robustness of Agentic Function Callingcited by 17
38 more
- 2025Towards Enforcing Company Policy Adherence in Agentic Workflowscited by 17
- 2025Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstractioncited by 15
- 2025Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Riskcited by 13
- 2025Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agentscited by 12
- 2025Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agentscited by 10
- 2025How Personality Traits Shape LLM Risk-Taking Behaviourcited by 8
- 2025AgentDNS: A Root Domain Naming System for LLM Agentscited by 8
- 2025ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanismcited by 8
- 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agentscited by 8
- 2026SoK: Security of Autonomous LLM Agents in Agentic Commercecited by 8
- 2026Agentic Trading: When LLM Agents Meet Financial Marketscited by 7
- 2024A Survey of Financial AI: Architectures, Advances and Open Challengescited by 6
- 2025Emergent Bias and Fairness in Multi-Agent Decision Systemscited by 5
- 2026Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awarenesscited by 5
- 2026ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Queryingcited by 5
- 2025Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challengescited by 4
- 2025Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Tradingcited by 4
- 2024Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoningcited by 3
- 2025MASCA: LLM based-Multi Agents System for Credit Assessmentcited by 3
- 2025Language Model Guided Reinforcement Learning in Quantitative Tradingcited by 3
- 2026TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agentscited by 3
- 2026FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarioscited by 3
- 2025FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Toolscited by 2
- 2025To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisionscited by 2
- 2025Can Large Language Models Develop Gambling Addiction?cited by 2
- 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
- 2026MemPot: Defending Against Memory Extraction Attack with Optimized Honeypotscited by 2
- 2026Self-Sovereign Agentcited by 2
- 2026Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experimentcited by 2
- 2026Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documentscited by 2
- 2025CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Modelscited by 1
- 2025General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Actingcited by 1
- 2025BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation formatcited by 1
- 2025Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMscited by 1
- 2025Risk Profiling and Modulation for LLMscited by 1
- 2025Banking Done Right: Redefining Retail Banking with Language-Centric AIcited by 1
- 2026ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologiescited by 1
- 2026Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Modelscited by 1
50 most cited of 60 All 60 (JSON)
- 2026Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing26 Sep 2026
- 2026SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes17 Sep 2026
- 2026E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning13 Sep 2026
- 2026ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance20 Aug 2026
- 2026Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents6 Aug 2026
- 2026Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior10 Jun 2026
- 2026Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems6 Jun 2026
- 2026Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents3 Jun 2026
- 2026FundaPod: A Multi-Persona Agent Pod Architecture with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research27 May 2026
- 2026Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment20 May 2026
- 2026Agentic Trading: When LLM Agents Meet Financial Markets19 May 2026
- 2026FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios1 May 2026
38 more
- 2026Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models18 Apr 2026
- 2026SoK: Security of Autonomous LLM Agents in Agentic Commerce15 Apr 2026
- 2026ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying10 Apr 2026
- 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agents5 Apr 2026
- 2026Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness29 Mar 2026
- 2026TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents23 Mar 2026
- 2026Self-Sovereign Agent4 Mar 2026
- 2026ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies16 Feb 2026
- 2026MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots7 Feb 2026
- 2025Emergent Bias and Fairness in Multi-Agent Decision Systems18 Dec 2025
- 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution11 Dec 2025
- 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents20 Oct 2025
- 2025Banking Done Right: Redefining Retail Banking with Language-Centric AI9 Oct 2025
- 2025Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading6 Oct 2025
- 2025Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents28 Sep 2025
- 2025Risk Profiling and Modulation for LLMs27 Sep 2025
- 2025Can Large Language Models Develop Gambling Addiction?26 Sep 2025
- 2025Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs17 Sep 2025
- 2025FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning16 Sep 2025
- 2025Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning16 Sep 2025
- 2025BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format2 Sep 2025
- 2025EconAgentic in DePIN Markets: A Large Language Model Approach to the Sharing Economy of Decentralized Physical Infrastructure29 Aug 2025
- 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios25 Aug 2025
- 2025Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework15 Aug 2025
- 2025Language Model Guided Reinforcement Learning in Quantitative Trading4 Aug 2025
- 2025ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism1 Aug 2025
- 2025MASCA: LLM based-Multi Agents System for Credit Assessment30 Jul 2025
- 2025Towards Enforcing Company Policy Adherence in Agentic Workflows22 Jul 2025
- 2025To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions11 Jul 2025
- 2025Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challenges7 Jul 2025
- 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents20 Jun 2025
- 2025General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting20 Jun 2025
- 2025AgentDNS: A Root Domain Naming System for LLM Agents28 May 2025
- 2025CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models27 May 2025
- 2025Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstraction26 May 2025
- 2025LLM-Powered AI Agent Systems and Their Applications in Industry22 May 2025
- 2025Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agents14 May 2025
- 2025Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?11 May 2025
50 newest of 60 All 60 (JSON)
- 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
- 2025Agentic Large Language Models, a surveycited by 105
- 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agentscited by 82
- 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutioncited by 65
- 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
- 2025Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Frameworkcited by 25
- 2025LLM-Powered AI Agent Systems and Their Applications in Industrycited by 22
- 2025On the Robustness of Agentic Function Callingcited by 17
- 2025Towards Enforcing Company Policy Adherence in Agentic Workflowscited by 17
- 2025Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Riskcited by 13
- 2025Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agentscited by 10
- 2025AgentDNS: A Root Domain Naming System for LLM Agentscited by 8
12 most cited of 31 All 31 (JSON)
- 2026Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing26 Sep 2026
- 2026SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes17 Sep 2026
- 2026ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance20 Aug 2026
- 2026Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents6 Aug 2026
- 2026Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems6 Jun 2026
- 2026FundaPod: A Multi-Persona Agent Pod Architecture with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research27 May 2026
- 2026Agentic Trading: When LLM Agents Meet Financial Markets19 May 2026
- 2026SoK: Security of Autonomous LLM Agents in Agentic Commerce15 Apr 2026
- 2026ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying10 Apr 2026
- 2026Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness29 Mar 2026
- 2026TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents23 Mar 2026
- 2026Self-Sovereign Agent4 Mar 2026
12 newest of 31 All 31 (JSON)
- 2025Efficient Inference for Large Reasoning Models: A Surveycited by 58
- 2025FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoningcited by 26
- 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 25
- 2025Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstractioncited by 15
- 2024Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoningcited by 3
- 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
- 2025General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Actingcited by 1
- 2025Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMscited by 1
- 2026Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Modelscited by 1
- 2026Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behaviorcited by 1
- 2026E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoningcited by 0
- 2026E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning13 Sep 2026
- 2026Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior10 Jun 2026
- 2026Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models18 Apr 2026
- 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents20 Oct 2025
- 2025Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs17 Sep 2025
- 2025FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning16 Sep 2025
- 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios25 Aug 2025
- 2025General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting20 Jun 2025
- 2025Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstraction26 May 2025
- 2025Efficient Inference for Large Reasoning Models: A Survey29 Mar 2025
- 2024Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning16 Oct 2024
- 2025Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?cited by 19
- 2025How Personality Traits Shape LLM Risk-Taking Behaviourcited by 8
- 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agentscited by 8
- 2024A Survey of Financial AI: Architectures, Advances and Open Challengescited by 6
- 2025Emergent Bias and Fairness in Multi-Agent Decision Systemscited by 5
- 2025Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challengescited by 4
- 2025Language Model Guided Reinforcement Learning in Quantitative Tradingcited by 3
- 2025Can Large Language Models Develop Gambling Addiction?cited by 2
- 2026MemPot: Defending Against Memory Extraction Attack with Optimized Honeypotscited by 2
- 2026Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experimentcited by 2
- 2026Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documentscited by 2
- 2025CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Modelscited by 1
12 most cited of 16 All 16 (JSON)
- 2026Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents3 Jun 2026
- 2026Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment20 May 2026
- 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agents5 Apr 2026
- 2026MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots7 Feb 2026
- 2025Emergent Bias and Fairness in Multi-Agent Decision Systems18 Dec 2025
- 2025Risk Profiling and Modulation for LLMs27 Sep 2025
- 2025Can Large Language Models Develop Gambling Addiction?26 Sep 2025
- 2025Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning16 Sep 2025
- 2025BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format2 Sep 2025
- 2025EconAgentic in DePIN Markets: A Large Language Model Approach to the Sharing Economy of Decentralized Physical Infrastructure29 Aug 2025
- 2025Language Model Guided Reinforcement Learning in Quantitative Trading4 Aug 2025
- 2025Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challenges7 Jul 2025
12 newest of 16 All 16 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2025Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents
- 2025When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents
- 2025StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
- 2026Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
- 2024INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent
- 2024TraderTalk: An LLM Behavioural ABM applied to Simulating Human Bilateral Trading Interactions
- 2023FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design
- 2025StockSim: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent LLMs in Financial Markets