Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· 0 citations· 35 references
TL;DR
This work proposes Scenario-Context Rollout (SCR), a macroeconomics-guided feedback mechanism to produce a distribution of next-day joint returns under potential economic shocks, and theoretically analyze this problem and shows that combining scenario-scored rewards with tape-realized transitions induces a hybrid fixed point.
Abstract
When economic structures and market dynamics shift, classic portfolio rebalancing algorithms often suffer from unstable and degraded performance. To improve the return and robustness of portfolio management, we explore reinforcement learning (RL) and propose Scenario-Context Rollout (SCR), a macroeconomics-guided feedback mechanism to produce a distribution of next-day joint returns under potential economic shocks. However, doing so faces new challenges, as history will never tell what would have happened differently. As a result, incorporating scenario-based rewards from rollouts introduces a reward-transition mismatch in temporal-difference (TD) learning, destabilizing RL critic training. We theoretically analyze this problem and show that combining scenario-scored rewards with tape-realized transitions induces a hybrid fixed point. Guided by this analysis, we construct a counterfactual next state using the SCR continuations and augment the critic agent's bootstrap target. Doing so stabilizes the learning and provides a viable bias-variance tradeoff. In out-of-sample evaluations across 31 distinct universes of U.S. equity and ETF portfolios, our method improves Sharpe ratio by up to 76% and reduces maximum drawdown by up to 53% compared with classic and RL-based portfolio rebalancing baselines.
A closed-loop multi-agent decision framework that introduces prompt-level learning as a scalable alternative to full model retraining and highlights the potential of prompt-level adaptation for building robust and autonomous financial decision systems.
Kandarp Mukeshkumar Sharda, Aliyu Sani Sambo· NLP & Big Data· 0 citations
This paper introduces a dynamic portfolio optimization framework for large institutional investors using Scientific Physics-Informed Reinforcement Learning (SciPhyRL). Formulated in continuous time over an extended state space that includes explicit cumulative costs, the approach leverages offline historical data to learn optimal, distribution-aware strategies. A core innovation reduces the optimization challenge to solving an HJB equation by projecting it onto observed trajectories as a pathwise Hamilton-Jacobi equation. This is solved directly from data using PINN in a single offline sweep, eliminating the need for traditional value or policy iteration. To make the method effective at practical short horizons, the control variable is recast from a continuous trading rate to a discrete target holding. This ensures signal-implied positions are reached immediately, while execution costs are evaluated against a microstructure-grounded quadratic price impact model. Evaluated on a $14$-asset ETF universe using an engineered oracle signal, the learned Gibbs policy yields substantial out-of-sample Sharpe ratio improvements over static and myopic baselines. The results demonstrate that the proposed framework successfully translates known signal quality into a robust, multi-period, and cost-aware allocation mechanism with strictly controlled volatility and turnover.
Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as UniswapV3, are now a well-established design. In these markets, liquidity providers (LPs) face a sequential decision problem: they must decide when to rebalance their positions and which price ranges to allocate capital to as market conditions evolve. We formulate dynamic liquidity provision as a stochastic impulse control problem and use reinforcement learning (RL) to solve it, focusing on providing interpretable solutions. We show that learned policies exhibit rich state-dependent behaviour, allocating liquidity according to mispricing, rebalancing costs, uncertainty, inventory exposure, and heterogeneous risk preferences. These behaviours help compress the left tail of the Profit and Loss (PnL) distribution and avoid catastrophic outcomes under high uncertainty. Finally, we benchmark the RL agents against baseline and sophisticated agents from the AMM microstructure literature and analyse their performance.
Georgios Chionas, Charalampos Kleitsikas, Stefanos Leonardos et al.· 0 citations
Market-neutral portfolios aim to generate consistent returns while offsetting systematic market risk. Traditional approaches based on factor models or convex optimization often underperform during market regime shifts or when structural assumptions break down. We propose AlphaZeroBeta, a deep reinforcement learning framework designed to deliver benchmark-relative alpha (excess returns) with near-zero beta (market neutrality). AlphaZeroBeta combines a composite reward function that balances risk-adjusted excess return, benchmark correlation, and transaction costs with a CNN-GRU policy trained end-to-end via Recurrent PPO and evaluated through a rolling walk-forward protocol. Backtests covering 2014-2024 across seven equity indices show that the model achieves higher Sharpe ratios than the baselines while maintaining near-zero benchmark correlations and competitive drawdowns.
The integration of Large Language Models (LLMs) with Reinforcement Learning (RL) for financial decision-making has grown rapidly in recent years, yet the literature remains fragmented and lacks systematic comparison across methods. In this survey we analyze 34 core studies (2023–2026), selected through a multi-stage process involving 84 initial candidates and 46 full-text reviews, and propose a three-paradigm taxonomy (feature-based, auxiliary-based, and policy-based) based on the functional role of LLMs within the RL pipeline. Analysis of these integration paradigms reveals an emergent architectural trade-off: while tighter policy-based coupling theoretically offers deeper contextual reasoning, it frequently introduces significant computational overhead and training instability. Conversely, simpler feature-based integration provides superior scalability and stability, though often at the expense of representational depth. Given the current benchmark fragmentation, the reported performance gains across these studies remain difficult to validate universally across different asset classes. Critical gaps identified include the insufficient handling of data leakage and look-ahead bias, standardized benchmarks, and limited alignment with regulatory frameworks such as MiFID II and the EU AI Act.
Ghusoon Hadi al-Aldaffaie, Alireza Taheri, Amirfarhad Farhadi et al.· Discover Artificial Intellig...· 0 citations
This work introduces NextFund, an evaluation platform that makes financial-agent behavior observable under live market conditions, and presents NextFund on Hong Kong, U.S., and China A-share equities, illustrating how inspectable decision histories enable fairer benchmarking and more actionable diagnosis.
Changlun Li, Peixian Ma, Qiqi Duan et al.· 0 citations