Explore all papers

5,749 papers

The filter tools did not load, so your filters are not applied: the list below is the plain, unfiltered list of papers.

Skip to results

FinNextAssist: Towards Professional Financial Deep Research Assistant

Li et al.

Deep Research (DR) agents have demonstrated strong capabilities in complex, research-oriented tasks through autonomous planning, iterative retrieval, multi-step reasoning, and structured reporting. However, adapting DR agents to finance introduces unique challenges: financial analysis demands the…

Holy Grail Math 6.0 Rigor 8.0
Costs: Not applicableOut-of-sample: UnclearResolution: Daily Data
More details
Authors
Xiangyu Li, Fengbin Zhu, Xuan Yao, Siyu Liu, Xiaoluan Liu, Chao Wang, Huanbo Luan, Xiaofen Xing, Xiangmin Xu, Ke-Wei Huang, Richang Hong, Tat-Seng Chua
Evaluation
Forecast accuracy

Landscape-Dependent Performance of Photonic Quantum Solvers in QUBO Feature Selection for Financial Risk Detection

Sahoo et al.

Feature selection for imbalanced classification tasks such as credit card fraud and consumer default detection requires balancing predictive relevance, inter-feature redundancy, and computational feasibility. We benchmark three computing paradigms, classical branch-and-bound optimization (Gurobi)…

Holy Grail Math 7.5 Rigor 8.0
Costs: Not applicableOut-of-sample: UnclearResolution: Unclear
More details
Authors
Nirvik Sahoo, Paul Robert Griffin
Evaluation
Forecast accuracy

MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code

Wang et al.

Large language models are moving from producing trading signals to writing the code that executes them. The failure mode of the second role is silent: generated code runs, a backtest plots, yet the risk logic that the trader described is not the logic being executed. Existing code benchmarks test…

Holy Grail Math 6.0 Rigor 9.0 Code
Costs: ModeledOut-of-sample: NoneResolution: Intraday Bars
More details
Authors
Siyu Wang, Yifan Wang, Yuecheng He
Evaluation
Unclear

Mixture-of-Experts for Cryptocurrency Order Execution: Training Stability, Tail Risk, and Failure Modes

Ardaiz et al.

Deep reinforcement-learning policies for order execution can vary substantially across training seeds, so apparent architectural gains may reflect favourable training realisations rather than reproducible properties of the architecture. We evaluate vanilla Double Deep Q-Learning (DDQL)…

Holy Grail Math 6.0 Rigor 8.0
Costs: UnclearOut-of-sample: HoldoutResolution: Unclear
More details
Authors
Alexander Ardaiz, Varun Budati, Ali Habibnia
Evaluation
Execution cost

Multi-Agent AI as a Nested Principal-Agent Problem in Private Wealth Management: Mandate Representation and Evidence Control in Switzerland, Germany and Austria

Kurz et al.

In private wealth management, a manager delegating to artificial intelligence (AI) acts as the client's agent and the system's principal. We introduce a model-independent formulation that combines nested principal–agent delegation with constrained joint maximisation as the task assigned to the AI…

Holy Grail Math 6.0 Rigor 6.0
More details
Authors
Walter Kurz, Reinhard Magg, Florian Kollberg, Wojtek Stricker, Stefan Marx, Frank Reinhardt, Velimir Dedić

PreFER: Interactive Robo-Advisor with Scoring Mechanism

Wang et al.

We propose an interactive robo-advising framework that learns personalized risk preferences from scores provided by clients. The resulting preference-learning problem is closely related to inverse reinforcement learning (IRL), as the robo-advisor infers the client's latent reward specification from…

Lab Rats Math 7.0 Rigor 3.0
More details
Authors
Yuwei Wang, Hoi Ying Wong

Priority Gas Auction Cadence and Searcher Competition: Evidence from Flashblocks on Base

Anchuri et al.

Flashblocks divide a block's priority gas auction into shorter sequential auctions that commit transaction order before the block is complete. We ask how this auction cadence affects bidding and competition among automated arbitrageurs, or searchers. In July 2025 Base replaced a single 2 s auction…

Holy Grail Math 7.5 Rigor 8.0
Costs: UnclearOut-of-sample: NoneResolution: Unclear
More details
Authors
Pranay Anchuri, Edward W. Felten, Akaki Mamageishvili
Evaluation
Unclear

Shapley-based Structural Analysis of Neural Calibration for Stochastic Volatility Models

Afzali et al.

Neural network-based approaches have emerged as efficient alternatives to traditional optimization-based procedures for the calibration of stochastic volatility models. However, existing work has focused primarily on predictive accuracy, with comparatively little attention devoted to understanding…

Holy Grail Math 7.5 Rigor 7.0
Costs: Not applicableOut-of-sample: UnclearResolution: Synthetic Data
More details
Authors
Shaïn Afzali, Serena Della Corte, Antonis Papapantoleon
Evaluation
Pricing / calibration

When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game

Wong et al.

Reinforcement learning (RL) is increasingly used for financial optimal-control problems when complex dynamics make analytical strategies difficult to obtain. There are financial mathematics literactures which provides many solved models whose equations and controls could evaluate and guide…

Holy Grail Math 7.5 Rigor 7.0
More details
Authors
Siu Tung Wong, Carlo Campajola

Certified Alpha Capacity: Statistical Evidence, Economic Lifetime, and Arbitrage under Decay

Bonacorsi

In this paper we study whether a trading signal can accumulate enough statistical evidence for reliable deployment before its economic value decays. We solve the problem by measuring statistical evidence and remaining opportunity on a common Kullback-Leibler information scale, obtaining an exact…

Holy Grail Math 9.0 Rigor 6.0
Costs: Not applicableOut-of-sample: UnclearResolution: Intraday Bars
More details
Evaluation
Forecast accuracy

Densities for scalar-valued BSDEs via unique continuation and backward uniqueness

Bourguin et al.

We give sufficient conditions ensuring that, at every fixed positive time, the scalar backward component of a Markovian forward-backward stochastic differential equation with multidimensional forward process admits a density with respect to Lebesgue measure. Existing density criteria for BSDEs…

Lab Rats Math 9.0 Rigor 2.0
More details
Authors
Solesne Bourguin, Daniel C. Schwarz

Distribution-constrained maximum stopping of maximum type

Deng et al.

We consider the distribution-constrained optimal stopping problem _τ~ μ E[B^*_τ], where μ is a probability distribution on R_+, and (B^*_t) denotes the running maximum of a standard Brownian motion. This problem was introduced in Beiglbock et al. (PTRF, 2018), where a monotonicity principle is used…

Lab Rats Math 9.0 Rigor 2.0
More details
Authors
Shuoqing Deng, Xin Zhang

Negative Oil & Nickel Squeeze: A Feedback Model for Extreme Commodity Futures Prices

Zimbidis et al.

On April 20, 2020, the May front-month WTI oil futures contract, one day before its expiration date, opened near $17/barrel and dropped far below zero in a single trading day, reaching an intraday low of -$40.32 and settling at -$37.63. Such market behavior was unforeseen at the time. This event…

Holy Grail Math 8.0 Rigor 6.0
Costs: Not applicableOut-of-sample: NoneResolution: Intraday Bars
More details
Authors
Iosif Zimbidis, Ronnie Sircar
Evaluation
Pricing / calibration

On the Pricing of American Options under Stochastic Local Volatility and Stochastic Correlation via the RBSDE Framework

Teng

In this work, we study the pricing of American options under stochastic local volatility (SLV) models extended by including stochastic correlation driven by an additional stochastic process. We generalize the class of SLV models by incorporating a flexible stochastic correlation structure. To price…

Holy Grail Math 9.0 Rigor 7.0
Costs: Not applicableOut-of-sample: NoneResolution: Synthetic Data
More details
Evaluation
Pricing / calibration

Portfolio Choice under General Utility with Transaction Costs and Search Frictions

Gang et al.

We study finite-horizon portfolio optimization with proportional transaction costs and trading opportunities arriving at the jump times of a Cox process. Borrowing and short-selling are prohibited, while utility functions need not be concave, increasing, or differentiable. The admissible class…

Lab Rats Math 9.0 Rigor 4.0
More details
Authors
Tae Ung Gang, Donghan Kim

PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading

Kien et al.

Reinforcement learning for trading often struggles to balance upside participation with drawdown control. Profit-only policies can collapse toward passive long exposure on upward-drifting assets, while aggressively risk-penalized rewards can become too defensive during volatile periods. This paper…

Holy Grail Math 6.0 Rigor 7.0 Code
Costs: ModeledOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Duong Hien Chi Kien, Thanh Trung Huynh
Evaluation
Trading P&L

Shared Models, Selective Trading, and Order Flow

Li et al.

We study whether model diversity survives selection into trading. In synthetic markets with a fixed mixture of three language-model families, news presentation changes their representation among submitted orders. At the announcement round, Qwen's share of submitted orders shifts by 48 percentage…

Holy Grail Math 6.0 Rigor 7.0
More details
Authors
Victoria Ruojie Li, Arka Prava Bandyopadhyay

Social welfare and price discovery in double auction markets

Pennanen

The tendency of the double auction mechanism to drive prices to competitive equilibrium has been well documented in laboratory experiments, but the phenomenon has lacked a theoretical explanation. This paper studies dynamic double auctions in a pure exchange economy where agents bid their…

Lab Rats Math 8.5 Rigor 2.0

Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents

Alzahrani

When developers change one component of an agent, such as its controller, a learned model or its verifier, they usually judge the change by an aggregate task score. That score cannot tell whether improvement was attainable, which component lost value, or what the agent's own checks certify. We…

Holy Grail Math 6.5 Rigor 8.0
Costs: ModeledOut-of-sample: Walk-forwardResolution: Synthetic Data
More details
Evaluation
Trading P&L

Exchange Rate Determination for Cryptocurrency Mergers: A Formal Framework

Sala et al.

Many of the thousands of existing cryptocurrencies suffer from declining adoption, low liquidity and weak security, and merging two of them into a single ecosystem is a natural alternative to abandonment. No rigorous framework exists, however, for determining a fair exchange rate in such a merger.…

Lab Rats Math 8.5 Rigor 3.0
More details
Authors
Massimiliano Sala, Daniela Visetti