{"total":87,"rows":[{"id":"2311.13743","title":"FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design","created":"2023-11-23","cited_by_count":164,"area":"agents"},{"id":"2402.18485","title":"A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist","created":"2024-02-28","cited_by_count":137,"area":null},{"id":"2407.06567","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","created":"2024-07-09","cited_by_count":113,"area":"agents"},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"area":"offlinerl"},{"id":"2405.14767","title":"FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models","created":"2024-05-23","cited_by_count":40,"area":"agents"},{"id":"2110.04471","title":"Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning","created":"2021-10-09","cited_by_count":29,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2505.15859","title":"AutoData: A Multi-Agent System for Open Web Data Collection","created":"2025-05-21","cited_by_count":25,"area":"agents"},{"id":"2110.04156","title":"Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters","created":"2021-10-08","cited_by_count":24,"area":"offlinerl"},{"id":"2505.11065","title":"Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking","created":"2025-05-16","cited_by_count":21,"area":null},{"id":"2203.10591","title":"Policy Gradients using Variational Quantum Circuits","created":"2022-03-20","cited_by_count":15,"area":null},{"id":"2304.13174","title":"Dynamic Datasets and Market Environments for Financial Reinforcement Learning","created":"2023-04-25","cited_by_count":15,"area":null},{"id":"2409.05144","title":"QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCE","created":"2024-09-08","cited_by_count":14,"area":"deeprl"},{"id":"2411.12746","title":"A Review of Reinforcement Learning in Financial Applications","created":"2024-11-01","cited_by_count":13,"area":"deeprl"},{"id":"2411.00782","title":"TradExpert: Revolutionizing Trading with Mixture of Expert LLMs","created":"2024-10-16","cited_by_count":12,"area":"moe"},{"id":"2112.05923","title":"ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning","created":"2021-12-11","cited_by_count":9,"area":null},{"id":"2507.09255","title":"StockSim: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent LLMs in Financial Markets","created":"2025-07-12","cited_by_count":8,"area":"agents"},{"id":"2508.17565","title":"TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis","created":"2025-08-25","cited_by_count":8,"area":"agents"},{"id":"2311.10801","title":"Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools","created":"2023-11-17","cited_by_count":7,"area":null},{"id":"2406.14537","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","created":"2024-06-20","cited_by_count":7,"area":"deeprl"},{"id":"2512.23515","title":"Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2605.19337","title":"Agentic Trading: When LLM Agents Meet Financial Markets","created":"2026-05-19","cited_by_count":7,"area":"agents"},{"id":"2111.03995","title":"Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach","created":"2021-11-07","cited_by_count":5,"area":null},{"id":"2302.00586","title":"PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets","created":"2023-01-14","cited_by_count":5,"area":"moe"},{"id":"2303.10382","title":"Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management","created":"2023-03-18","cited_by_count":4,"area":null},{"id":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2403.16667","title":"Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization","created":"2024-03-25","cited_by_count":4,"area":"deeprl"},{"id":"2503.18313","title":"Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2508.02292","title":"FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2510.04787","title":"Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2309.02632","title":"Deep Reinforcement Learning from Hierarchical Preference Design","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2407.14486","title":"Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent","created":"2024-07-19","cited_by_count":3,"area":"deeprl"},{"id":"2508.02366","title":"Language Model Guided Reinforcement Learning in Quantitative Trading","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2509.12753","title":"DeltaHedge: A Multi-Agent Framework for Portfolio Options Optimization","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2510.27251","title":"FinPos: A Position-Aware Trading Agent System for Real Financial Markets","created":"2025-10-31","cited_by_count":3,"area":"agents"},{"id":"2605.28850","title":"Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2206.14267","title":"Applications of Reinforcement Learning in Finance -- Trading with a Double Deep Q-Network","created":"2022-06-28","cited_by_count":2,"area":null},{"id":"2207.02134","title":"Balancing Profit, Risk, and Sustainability for Portfolio Management","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2307.07666","title":"Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2307.09631","title":"Deep Reinforcement Learning for ESG financial portfolio management","created":"2023-06-19","cited_by_count":2,"area":null},{"id":"2505.03760","title":"Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach","created":"2025-04-20","cited_by_count":2,"area":"deeprl"},{"id":"2601.03948","title":"Trade-R1: Bridging Verifiable Rewards to Stochastic Environments via Process-Level Reasoning Verification","created":"2026-01-07","cited_by_count":2,"area":"lr"},{"id":"2602.17098","title":"Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization","created":"2026-02-19","cited_by_count":2,"area":"deeprl"},{"id":"2604.10974","title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","created":"2026-04-13","cited_by_count":2,"area":"deeprl"},{"id":"2606.30997","title":"A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management","created":"2026-06-30","cited_by_count":2,"area":"moe"},{"id":"2201.05906","title":"Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets","created":"2022-01-15","cited_by_count":1,"area":null},{"id":"2206.05910","title":"Safe-FinRL: A Low Bias and Variance Deep Reinforcement Learning Implementation for High-Freq Stock Trading","created":"2022-06-13","cited_by_count":1,"area":null},{"id":"2306.09746","title":"Finite-Time Analysis of Temporal Difference Learning with Experience Replay","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2311.00859","title":"Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2402.01441","title":"Learning the Market: Sentiment-Based Ensemble Trading Agents","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2407.16103","title":"Reinforcement Learning Pair Trading: A Dynamic Scaling approach","created":"2024-07-23","cited_by_count":1,"area":"deeprl"},{"id":"2503.04143","title":"MTS: A Deep Reinforcement Learning Portfolio Management Framework with Time-Awareness and Short-Selling","created":"2025-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2508.01173","title":"MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2604.10911","title":"EvoNash-MARL: A Closed-Loop Multi-Agent Reinforcement Learning Framework for Medium-Horizon Equity Allocation","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.10996","title":"When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.12653","title":"Plan Before You Trade: Inference-Time Optimization for RL Trading Agents","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2608.26990","title":"DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock Research","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2203.11318","title":"Deep Reinforcement Learning and Convex Mean-Variance Optimisation for Portfolio Management","created":"2022-02-13","cited_by_count":0,"area":null},{"id":"2412.17908","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","created":"2024-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2502.07280","title":"MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management","created":"2025-02-11","cited_by_count":0,"area":"deeprl"},{"id":"2504.16635","title":"Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models","created":"2025-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2505.21536","title":"CiRL: Open-Source Environments for Reinforcement Learning in Circular Economy and Net Zero","created":"2025-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2507.19639","title":"Directly Learning Stock Trading Strategies Through Profit Guided Loss Functions","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.08329","title":"Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2509.12048","title":"Hi-DARTS: Hierarchical Dynamically Adapting Reinforcement Trading System","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2510.10526","title":"Integrating Large Language Models and Reinforcement Learning for Sentiment-Driven Quantitative Trading","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.13792","title":"Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach","created":"2025-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2510.14985","title":"DeepAries: Adaptive Rebalancing Interval Selection for Enhanced Portfolio Selection","created":"2025-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2603.21330","title":"FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"agents"},{"id":"2604.00031","title":"Decomposable Reward Modeling and Realistic Environment Design for Reinforcement Learning-Based Forex Trading","created":"2026-03-20","cited_by_count":0,"area":"alignment"},{"id":"2604.14495","title":"Decoupling Identity from Utility: Privacy-by-Design Frameworks for Financial Ecosystems","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.06730","title":"Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.23978","title":"Algometrics: Forecasting Under Algorithmic Feedback","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.24490","title":"Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.04574","title":"Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.10448","title":"Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations","created":"2026-06-09","cited_by_count":0,"area":"deeprl"},{"id":"2607.15414","title":"AI Trading: Evaluating Large Language Models for Technical Market Analysis","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.05255","title":"An Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language Goals","created":"2026-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.05668","title":"F$^2$Agent: Financial Fusion of Agentic Intelligence for Multimodal Trading","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.11232","title":"Backtrader-Bench: Benchmarking LLM Agents on Algorithmic Trading with Self-Generated MCQs","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2609.07065","title":"VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha Discovery","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.13825","title":"ViperQ: Order Flow Pattern Recognition via Auction Market Theory for Reinforcement Learning Trading","created":"2026-09-12","cited_by_count":0,"area":"deeprl"},{"id":"2610.01325","title":"PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}