Search the finance research feed.
ARXIV · 2026 · arXiv
An institution must complete a portfolio adjustment, but traders who prepare inventory for it can choose whether to participate. We study how public forecasts affect the institution's cost in a Bayesian execution game with optional activation, transient impact, and uniform-price terminal completion. The curvature of…
Authors: Khizar Qureshi
Citations: N/A
q-fin.TRmath.OCq-fin.MF
ARXIV · 2026 · arXiv
Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecasting models and alpha discovery help identify opportunities. However, traditional pipelines often decouple signal foreca…
Authors: Annan Wang, Yuchen Xie, Yu Cen, Leon Liangyu Chen, Qianyu Julie Zhu, Xin Li, Tianyi Wei, Weisi Lin
Citations: N/A
cs.LGq-fin.TR
ARXIV · 2026 · arXiv
Papers on large-language-model (LLM) trading agents and alpha mining report Sharpe ratios that would be remarkable in any other part of empirical finance. We audit the evidence behind those numbers. Before coding a single paper we pre-registered a population of 91 papers from a curated corpus of LLM trading research…
Authors: Henry Zhang
Citations: N/A
q-fin.CPq-fin.GNq-fin.TR
ARXIV · 2026 · arXiv
Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcripts. Across 260 simulations, the agent is asked to collude on the price of silver by a…
Authors: Harrison C. Margolin
Citations: N/A
cs.AIcs.CLcs.MAecon.GNq-fin.TR
ARXIV · 2026 · arXiv
We study seasonality as a factor for predicting risk-adjusted returns across global futures markets. We document five seasonality anomalies that, in aggregate, are pervasive across bond, commodity and equity markets. We demonstrate that each seasonality factor produces excess returns that are not reasonably explaine…
Authors: Andrew Butler, Adam Butler, Maciej Zawadzki
Citations: N/A
q-fin.MFq-fin.PMq-fin.ST
ARXIV · 2026 · arXiv
Generative models have become the standard approach in language and vision. These models are typically pretrained first and then fine-tuned. Recent work demonstrates how to pretrain an autoregressive generative model on Level-3 order-flow data. However, to our knowledge, no one has fine-tuned such a model yet for do…
Authors: Fedor Shabashev
Citations: N/A
q-fin.TR
ARXIV · 2026 · arXiv
Market makers play a vital role in ensuring efficient trade within financial markets. Recent literature has delved into training market-making systems using reinforcement learning. This paper delves into the impact of various loss function formulations on risk management behavior within reinforcement-based market ma…
Authors: Siddharth Nand, Bora Guney
Citations: N/A
cs.LGq-fin.CPq-fin.TR
ARXIV · 2026 · arXiv
The limit order book (LOB) records outstanding buy and sell orders across multiple price levels. Its state evolves over time across market side, price level, and order attribute, naturally forming a multiway structure. However, existing LOB models typically flatten these dimensions into a matrix model, thus obscurin…
Authors: Yuxuan Gu, Danilo Mandic
Citations: N/A
cs.LGq-fin.ST
ARXIV · 2026 · arXiv
We develop a no-arbitrage framework to recover implied fee rates from option-implied information and quantify fee compensation for liquidity providers in automated market maker (AMM) pools. Expected accumulated fees equal the current pool value minus the risk-neutral value of its terminal payoff, reducing forward-lo…
Authors: Diogo Duarte, Lucas X. Ferreira, Emmanuel Gobet, Yuri F. Saporito
Citations: N/A
q-fin.PR
ARXIV · 2026 · arXiv
Trading discipline often fails people. Our study tested whether four AI trading agents followed their strategies and risk rules. Offering traders the evidence and an agent evaluation toolkit to separate luck from following the rules, before giving agents meaningful autonomy or capital. Our study analysed 2,627 close…
Authors: Saad Naja, Nasser Odtallah, Jake Van-Praag, Sarah May
Citations: N/A
cs.AIcs.LGcs.MAq-fin.RMq-fin.TR
ARXIV · 2026 · arXiv
Financial institutions increasingly require intelligent risk-management systems that combine predictive performance with data reliability, interpretability, and adaptable decision policies for emerging agentic commerce environments. This study proposes a Trusted Financial Data (TFD) Multi-Agent Framework that integr…
Authors: Kayode Lateef Ogunsusi, Mary Nwaife Mezue, Kazeem Busayo Ogunsusi, Adeniyi Paul Phillips
Citations: N/A
q-fin.RM
ARXIV · 2026 · arXiv
Schmelzer and Hastie prove that Markowitz's Critical Line Algorithm and the LASSO path trace the same curve. This companion note checks that result numerically with a stock LASSO solver, \texttt{lars\_path} from \texttt{scikit-learn}, and no portfolio software. It covers long--short portfolios under a leverage cap,…
Authors: Thomas Schmelzer
Citations: N/A
q-fin.CPstat.ME
ARXIV · 2026 · arXiv
Signal correlation and PnL correlation are correlations over different index sets - across assets at each date versus across dates for scalar payoffs - and practitioners often treat the first as a proxy for the second. We give an exact decomposition that shows what that proxy sees and what it discards. We recall tha…
Authors: Marc Nunes
Citations: N/A
math.STq-fin.PM
ARXIV · 2026 · arXiv
Optimal execution (OE) in multi-asset settings involves complex interactions across assets, particularly through shared capital constraints during portfolio rebalancing. While existing models capture cross-impact and portfolio-level dynamics, they largely overlook the role of explicit cash constraints along the exec…
Authors: Ryuji Hashimoto, Namid R. Stillman
Citations: N/A
q-fin.TRcs.CEmath.OCq-fin.CPq-fin.RM
ARXIV · 2026 · arXiv
We estimate Kyle's (1985) price-impact coefficient $λ$ directly from daily equity order flow and test its ability to forecast the cross-section of subsequent stock returns. Using CRSP data from 2020 to 2025, we construct firm-month measures of signed order flow and two estimators of $\hatλ_{it}$: a within-month pric…
Authors: Irene Aldridge
Citations: N/A
econ.EMq-fin.PRq-fin.STq-fin.TR
ARXIV · 2026 · arXiv
This paper argues that AI-agent alignment in markets should not be understood only as a property of agents, but also as a property of the interaction infrastructure in which agents act. In financial markets, this infrastructure is the market core: the rule system that determines how orders enter, interact, match, pe…
Authors: Omar Inverso, Emilio Tuosto, Dragisa Zunic
Citations: N/A
cs.GTq-fin.TR
ARXIV · 2026 · arXiv
Simulating financial markets at scale with multi-agent (Agent-Based) models is critical for market design, regulatory stress-testing, and reinforcement learning, but traditional CPU simulators are bottlenecked by sequential processing while vectorized GPU frameworks suffer from kernel-launch overhead and redundant g…
Authors: Shakya Jayakody, Prarthinie Jayakody
Citations: N/A
cs.DCcs.PFq-fin.TR
ARXIV · 2026 · arXiv
We introduce the Polymarket-v1 Database: the complete on-chain trade archive of Polymarket's first-generation CTF Exchange on Polygon, spanning 2022-11-21 to 2026-04-28 and covering the full contract lifecycle from first settlement to natural termination. The dataset comprises 1.20 billion trade records across 1.30…
Authors: Boka Qin, Rui Yang
Citations: N/A
cs.CEq-fin.STq-fin.TR
ARXIV · 2026 · arXiv
We study a speculative trading problem within the exploratory reinforcement learning (RL) framework of Wang et al. [2020]. The problem is formulated as a sequential optimal stopping problem over entry and exit times under general utility function and price process. We first consider a relaxed version of the problem…
Authors: Yun Zhao, Alex S. L. Tse, Harry Zheng
Citations: N/A
q-fin.MFcs.LGmath.OCq-fin.CPq-fin.TR
ARXIV · 2026 · arXiv
The multidimensional Uncertain Volatility Model leads to robust option pricing problems under joint volatility and correlation uncertainty. Their numerical resolution quickly becomes challenging because the associated stochastic control problem is high-dimensional. We propose a backward actor-critic stochastic polic…
Authors: Lokman A Abbas-Turki, Jean-François Chassagneux, Jean-Philippe Lemor, Grégoire Loeper, Simon Sananes
Citations: N/A
q-fin.CPmath.PRq-fin.PR
ARXIV · 2026 · arXiv
Recent works have increasingly applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena. However, a crucial question arises: Do LLM agents' behaviors align with real market participants? This alignment is key to the val…
Authors: Zeping Li, Guancheng Wan, Keyang Chen, Yu Chen, Yiwen Zhao, Philip Torr, Guangnan Ye, Zhenfei Yin
Citations: N/A
q-fin.TRcs.AI
ARXIV · 2025 · arXiv
Accurately forecasting central bank policy decisions, particularly those of the Federal Open Market Committee(FOMC) has become increasingly important amid heightened economic uncertainty. While prior studies have used monetary policy texts to predict rate changes, most rely on static classification models that overl…
Authors: Kaito Takano, Masanori Hirano, Kei Nakagawa
Citations: N/A
q-fin.CPcs.AIcs.MA
ARXIV · 2025 · arXiv
Foundation models - already transformative in domains such as natural language processing - are now starting to emerge for time-series tasks in finance. While these pretrained architectures promise versatile predictive signals, little is known about how they shape the risk profiles of the trading strategies built at…
Authors: Jinrui Zhang
Citations: N/A
cs.CEq-fin.TR
ARXIV · 2025 · arXiv
This study introduces geometric algebra to decompose credit system relationships into their projective (correlation-like) and rotational (feedback-spiral) components. We represent economic states as multi-vectors in Clifford algebra, where bivector elements capture the rotational coupling between unemployment, consu…
Authors: Agus Sudjianto, Sandi Setiawan
Citations: N/A
q-fin.GNcs.LG