Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling

• URL: http://arxiv.org/abs/2602.19919v2
• Date: Fri, 27 Feb 2026 08:50:00 GMT
• Title: Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling
• Authors: Xiang Li, Zikai Wei, Yiyan Qi, Wanyun Zhou, Xiang Liu, Penglei Sun, Jian Guo, Yongqi Zhang, Xiaowen Chu,
• Abstract summary: Janus-Q is an end-to-end event-driven trading framework.<n>It unifies event-centric data construction and model optimization under a two-stage paradigm.<n>It achieves more consistent, interpretable, and profitable trading decisions than market indices.
• Score: 29.111030768419187
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Financial market movements are often driven by discrete financial events conveyed through news, whose impacts are heterogeneous, abrupt, and difficult to capture under purely numerical prediction objectives. These limitations have motivated growing interest in using textual information as the primary source of trading signals in learning-based systems. Two key challenges hinder existing approaches: (1) the absence of large-scale, event-centric datasets that jointly model news semantics and statistically grounded market reactions, and (2) the misalignment between language model reasoning and financially valid trading behavior under dynamic market conditions. To address these challenges, we propose Janus-Q, an end-to-end event-driven trading framework that elevates financial news events from auxiliary signals to primary decision units. Janus-Q unifies event-centric data construction and model optimization under a two-stage paradigm. Stage I focuses on event-centric data construction, building a large-scale financial news event dataset comprising 62,400 articles annotated with 10 fine-grained event types, associated stocks, sentiment labels, and event-driven cumulative abnormal return (CAR). Stage II performs decision-oriented fine-tuning, combining supervised learning with reinforcement learning guided by a Hierarchical Gated Reward Model (HGRM), which explicitly captures trade-offs among multiple trading objectives. Extensive experiments demonstrate that Janus-Q achieves more consistent, interpretable, and profitable trading decisions than market indices and LLM baselines, improving the Sharpe Ratio by up to 102.0% while increasing direction accuracy by over 17.5% compared to the strongest competing strategies.

Related papers

• Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets [57.179679246370114]
  In financial applications, reinforcement learning (RL) agents are commonly trained on historical data, where their actions do not influence prices.<n>During deployment, these agents trade in live markets where their own transactions can shift asset prices, a phenomenon known as market impact.<n>Traditional robust RL approaches address this model misspecification by optimizing the worst-case performance over a set of uncertainties.<n>We develop a novel class of elliptic uncertainty sets, enabling efficient and tractable robust policy evaluation.
  arXiv  Detail & Related papers  (2025-10-22T18:22:25Z)
• News-Aware Direct Reinforcement Trading for Financial Markets [4.651395723728895]
  In this work, we use the news sentiment scores derived from large language models, together with raw price and volume data, as observable inputs for reinforcement learning.<n>These inputs are processed by sequence models such as recurrent neural networks or Transformers to make end-to-end trading decisions.<n>The results demonstrate that our news-aware approach, which does not depend on handcrafted features or manually designed rules, can achieve performance superior to market benchmarks.
  arXiv  Detail & Related papers  (2025-10-22T02:17:03Z)
• TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis [15.865159423176982]
  TradingGroup is a multi-agent trading system designed to address limitations through a self-reflective architecture and an end-to-end data-synthesis pipeline.<n> TradingGroup consists of specialized agents for news sentiment analysis, financial report interpretation, stock trend forecasting, trading style adaptation, and a trading decision making agent.<n>Specifically, we design self-reflection mechanisms for the stock forecasting, style, and decision-making agents to distill past successes and failures for similar reasoning in analogous future scenarios.
  arXiv  Detail & Related papers  (2025-08-25T00:29:58Z)
• Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation [55.2788567621326]
  We introduce a novel benchmark, FIN-FORCE-FINancial FORward Counterfactual Evaluation.<n>By curating financial news headlines, FIN-FORCE supports LLM based forward counterfactual generation.<n>This paves the way for scalable and automated solutions for exploring and anticipating future market developments.
  arXiv  Detail & Related papers  (2025-05-26T02:41:50Z)
• STORM: A Spatio-Temporal Factor Model Based on Dual Vector Quantized Variational Autoencoders for Financial Trading [55.02735046724146]
  In financial trading, factor models are widely used to price assets and capture excess returns from mispricing.<n>We propose a Spatio-Temporal factOR Model based on dual vector quantized variational autoencoders, named STORM.<n>Storm extracts features of stocks from temporal and spatial perspectives, then fuses and aligns these features at the fine-grained and semantic level, and represents the factors as multi-dimensional embeddings.
  arXiv  Detail & Related papers  (2024-12-12T17:15:49Z)
• MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU [29.760324699979417]
  This paper proposes a stock prediction model, MCI-GRU, based on a multi-head cross-attention mechanism and an improved GRU.<n> Experiments on four main stock markets show that the proposed method outperforms SOTA techniques across multiple metrics.
  arXiv  Detail & Related papers  (2024-09-25T14:37:49Z)
• Market-GAN: Adding Control to Financial Market Data Generation with Semantic Context [23.773217528211905]
  Current financial datasets do not contain context labels. Current techniques are not designed to generate financial data with context as control. Market-GAN is a novel architecture incorporating a Generative Adversarial Networks (GAN) for the controllable generation with context.
  arXiv  Detail & Related papers  (2023-09-14T13:42:27Z)
• Bayesian Bilinear Neural Network for Predicting the Mid-price Dynamics in Limit-Order Book Markets [84.90242084523565]
  Traditional time-series econometric methods often appear incapable of capturing the true complexity of the multi-level interactions driving the price dynamics. By adopting a state-of-the-art second-order optimization algorithm, we train a Bayesian bilinear neural network with temporal attention. By addressing the use of predictive distributions to analyze errors and uncertainties associated with the estimated parameters and model forecasts, we thoroughly compare our Bayesian model with traditional ML alternatives.
  arXiv  Detail & Related papers  (2022-03-07T18:59:54Z)
• Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements [11.97251638872227]
  We propose a novel deep learning approach, named dual-CLVSA, to predict financial market movement with both trading data and the corresponding social sentiment measurements, each through a separate sequence-to-sequence channel. The experiment results show that dual-CLVSA can effectively fuse the two types of data, and verify that sentiment measurements are not only informative for financial market predictions, but they also contain extra profitable features to boost the performance of our predicting system.
  arXiv  Detail & Related papers  (2022-01-27T20:32:46Z)
• REST: Relational Event-driven Stock Trend Forecasting [76.08435590771357]
  We propose a relational event-driven stock trend forecasting (REST) framework, which can address the shortcoming of existing methods. To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts. To address the second shortcoming, we construct a stock graph and design a new propagation layer to propagate the effect of event information from related stocks.
  arXiv  Detail & Related papers  (2021-02-15T07:22:09Z)
• Gaussian process imputation of multiple financial series [71.08576457371433]
  Multiple time series such as financial indicators, stock prices and exchange rates are strongly coupled due to their dependence on the latent state of the market. We focus on learning the relationships among financial time series by modelling them through a multi-output Gaussian process.
  arXiv  Detail & Related papers  (2020-02-11T19:18:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.