{"total":58,"rows":[{"id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","created":"2023-06-09","cited_by_count":253,"area":null},{"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":"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":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2307.10485","title":"FinGPT: Democratizing Internet-scale Data for Financial Large Language Models","created":"2023-07-19","cited_by_count":67,"area":null},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"area":"alignment"},{"id":"2502.16789","title":"AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay","created":"2025-02-24","cited_by_count":42,"area":null},{"id":"2502.18834","title":"FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2502.11433","title":"FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2505.07078","title":"Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?","created":"2025-05-11","cited_by_count":20,"area":null},{"id":"2211.07400","title":"Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction","created":"2022-11-11","cited_by_count":18,"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":"2511.18850","title":"Cognitive Alpha Mining via LLM-Driven Code-Based Evolution","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2309.10654","title":"CFGPT: Chinese Financial Assistant with Large Language Model","created":"2023-09-19","cited_by_count":11,"area":null},{"id":"2305.18464","title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2112.06753","title":"FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance","created":"2021-12-13","cited_by_count":7,"area":null},{"id":"2303.11959","title":"Optimizing Trading Strategies in Quantitative Markets using Multi-Agent Reinforcement Learning","created":"2023-03-15","cited_by_count":7,"area":null},{"id":"2410.08870","title":"Can we hop in general? A discussion of benchmark selection and design using the Hopper environment","created":"2024-10-11","cited_by_count":7,"area":"deeprl"},{"id":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7,"area":"offlinerl"},{"id":"2309.10129","title":"Adaptive Liquidity Provision in Uniswap V3 with Deep Reinforcement Learning","created":"2023-09-18","cited_by_count":6,"area":null},{"id":"2402.16609","title":"Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization","created":"2024-02-23","cited_by_count":6,"area":"deeprl"},{"id":"2412.03038","title":"MILLION: A General Multi-Objective Framework with Controllable Risk for Portfolio Management","created":"2024-12-04","cited_by_count":6,"area":null},{"id":"2209.05559","title":"Deep Reinforcement Learning for Cryptocurrency Trading: Practical Approach to Address Backtest Overfitting","created":"2022-09-12","cited_by_count":5,"area":null},{"id":"2312.16248","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2401.04729","title":"Human Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information","created":"2024-01-09","cited_by_count":5,"area":null},{"id":"2503.04873","title":"Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?","created":"2025-03-06","cited_by_count":5,"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":"2507.00257","title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","created":"2025-06-30","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":"2307.09631","title":"Deep Reinforcement Learning for ESG financial portfolio management","created":"2023-06-19","cited_by_count":2,"area":null},{"id":"2501.06832","title":"A novel multi-agent dynamic portfolio optimization learning system based on hierarchical deep reinforcement learning","created":"2025-01-12","cited_by_count":2,"area":null},{"id":"2501.17992","title":"Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information","created":"2025-01-29","cited_by_count":2,"area":"deeprl"},{"id":"2602.00133","title":"PredictionMarketBench: A SWE-bench-Style Framework for Backtesting Trading Agents on Prediction Markets","created":"2026-01-28","cited_by_count":2,"area":"agents"},{"id":"2306.03985","title":"Agent Performing Autonomous Stock Trading under Good and Bad Situations","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2311.14061","title":"Towards Explainable Strategy Templates using NLP Transformers","created":"2023-11-23","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":"2410.14927","title":"Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution","created":"2024-10-19","cited_by_count":1,"area":null},{"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":"2211.03136","title":"Design Process is a Reinforcement Learning Problem","created":"2022-11-06","cited_by_count":0,"area":null},{"id":"2306.17598","title":"Navigation of micro-robot swarms for targeted delivery using reinforcement learning","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2309.00626","title":"An Ensemble Method of Deep Reinforcement Learning for Automated Cryptocurrency Trading","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2501.10709","title":"Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024","created":"2025-01-18","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":"2503.22575","title":"On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations","created":"2025-03-28","cited_by_count":0,"area":"deeprl"},{"id":"2505.12759","title":"Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2505.13188","title":"When a Reinforcement Learning Agent Encounters Unknown Unknowns","created":"2025-05-19","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":"2509.12048","title":"Hi-DARTS: Hierarchical Dynamically Adapting Reinforcement Trading System","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.00143","title":"Regime-Adaptive Continual Learning for Portfolio Management","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.10412","title":"A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis","created":"2026-06-09","cited_by_count":0,"area":"deeprl"},{"id":"2607.11141","title":"NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2608.15841","title":"Self-Supervised Auxiliary Task Discovery for Stable Reinforcement Learning in Stock Trading","created":"2026-08-16","cited_by_count":0,"area":"deeprl"},{"id":"2608.19974","title":"ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2609.28547","title":"PAWS: Policy-driven Agentic World Simulation","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.36914","title":"Can Language Models Learn to Forecast Stock Prices","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"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"},{"id":"2610.13998","title":"Enhanced Trading Systems with Intelligent Market Analysis","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}