Emilio Barucci, Yuheng Lan, Daniele Marazzina
Apr 23, 2026·q-fin.MF·PDF We investigate the optimal execution of contracts that are used in merger\&acquisition deals. We consider cash-settled and physically delivered contracts between a broker and a counterpart. Contracts are linear (total returns swaps), nonlinear (collar contracts) or Asian type (TWAP based contracts). We derive the optimal execution strategy and the optimal fee through indifference utility arguments allowing for linear market effects of trades. We show that linear cash-settled contracts are more expensive and more exposed to manipulation/statistical arbitrages by the broker. Also nonlinear and Asian type contracts are exposed to these phenomena.
Prakul Sunil Hiremath, Vruksha Arun Hiremath
Limit order books can transition rapidly from stable to stressed conditions, yet standard early-warning signals such as order flow imbalance and short-term volatility are inherently reactive. We formalise this limitation via a three-regime causal data-generating process (stable $\to$ latent build-up $\to$ stress) in which a latent deterioration phase creates a prediction window prior to observable stress. Under mild assumptions on temporal drift and regime persistence, we establish identifiability of the latent build-up regime and derive guarantees for strictly positive expected lead-time and non-trivial probability of early detection. We propose a trigger-based detector combining MAX aggregation of complementary signal channels, a rising-edge condition, and adaptive thresholding. Across 200 simulations, the method achieves mean lead-time $+18.6 \pm 3.2$ timesteps with perfect precision and moderate coverage, outperforming classical change-point and microstructure baselines. A preliminary application to one week of BTC/USDT order book data shows consistent positive lead-times while baselines remain reactive. Results degrade in low signal-to-noise and short build-up regimes, consistent with theory.
Ethan Ratliff-Crain, Colin M. Van Oort, Matthew T. K. Koehler, Brian F. Tivnan
Apr 22, 2026·q-fin.TR·PDF This study strengthens the foundations of multi-venue market modeling by attempting an independent replication of Wah and Wellman's 2016 model of latency arbitrage in a fragmented market. We find that faithful replication is hindered by missing implementation details in the original paper and limited quantitative reporting. We demonstrate that increasing the number of simulation runs beyond the original design allows for the creation of bootstrap confidence intervals to support rigorous tests of quantitative alignment, compensating for lacking distributional information (e.g. variance). We also demonstrate that increased complexity across the modeled scenarios corresponds with increased difficulty aligning to the original results. We draw on a codebase released by the original authors in connection with a later paper to recover additional implementation details; however, we reject quantitative alignment between that codebase and the published results. Combining information from the paper and the released code, we achieve relational equivalence for most metrics but reject quantitative alignment for model settings where latency is non-zero. We show that many of the qualitative takeaways from the original paper on the effects of market fragmentation and latency arbitrage are sensitive to the specifics of a `greedy strategy' extension given to the zero-intelligence (ZI) trader agents. Under an alternative interpretation of this strategy, we find that market fragmentation decreases execution times in all experiments and increases trader welfare in most experiments. Finally, to facilitate future replication, critique, and extension, we provide an ODD (Overview, Design concepts, Details) protocol for our implementations of the model.
Irene Aldridge, Gavhar Annaeva, Leyla Beriker, Zhiheng Cai, Samyak Choudhary, Camila Godoy, Kaicheng Gong, Zitao Huang, Jonah Ji, Hetvi Kharvasiya, Heng Li, Yuxuan Li, Tianchi Ma, Qingcheng Meng, Ruiyang Shi, Ananya Shrivastava, Jiaqi Wang, Yifan Wang, Zihua Wu, Jiayang Xu, Yuheng Yan, Zijun Zeng, Bowen Zhang, Francesco Zhang
Blockchain technology is widely expected to reduce transaction costs by automating contract enforcement and eliminating intermediaries; yet, the execution costs imposed by network congestion have received little attention in the operations management literature. We study on-chain peak shaving, the systematic scheduling of Ethereum transactions toward low-congestion windows to reduce gas fee exposure. We use transaction-level data from seven firms across seven industries (N = 62,142 transactions, January-March 2026). Gas fees vary significantly throughout the day: the peak-hour premium at 10 AM Eastern Time reaches USD 0.220 per transaction above the overnight baseline, driven primarily by speculative-arbitrage demand rather than operational activity. Firm-level scheduling responses are heterogeneous and not uniformly disciplined. Only three of seven firms transact disproportionately during off-peak hours; four transact counter-cyclically, concentrated in peak windows due to external deadlines or governance cycles. This heterogeneity is explained by two moderators: transaction deferrability and gas intensity. We formalize these into an On-Chain Scheduling Matrix that maps firms to four regimes: 1) full peak shaving, 2) selective peak shaving, 3) cost provisioning, and 4) accept-market-rate, with regime membership predicting both fee savings and residual cost floors (40-92 percent of actual expenditure). Theoretically, we extend Transaction Cost Economics to account for time-varying execution costs imposed by congestion externalities. In addition to extending Williamson's original cost taxonomy, we introduce a dual classification of gas fees as execution costs in timing but maladaptation costs in origin. The findings reposition on-chain gas-fee management alongside energy procurement and foreign exchange hedging as a domain requiring systematic operational planning.
Karl Svozil
Apr 14, 2026·q-fin.TR·PDF We investigate the impossibility of universally winning trading strategies -- those generating strict profit across all market trajectories -- through three distinct mathematical paradigms. Fundamentally, under standard admissibility constraints, the existence of such a strategy is a strict subset of strong arbitrage, which is mathematically precluded in competitive markets admitting an equivalent martingale measure. Beyond this rigorous measure-theoretic foundation, we explore analogous limitations in two alternative modeling regimes. Combinatorially, the No-Free-Lunch theorem demonstrates that outperformance requires exploitation of non-uniform market structure, as uniform averaging precludes universal dominance. Computationally, a Turing diagonalization argument constructs an adversarial environment that defeats any computable trading algorithm, shifting the impossibility from exogenous price paths to adaptive adversaries. These mathematical limits are framed by a time-reversal heuristic that establishes a formal analogy between financial martingale measures and thermodynamic detailed balance, resolving the Maxwell's Demon analogy for markets without relying on physically irrelevant Landauer erasure costs. Using the Wheel Options Strategy as a case study, we demonstrate that strategies succeeding ``for all practical purposes'' (FAPP) inherently depend on transient regime assumptions, meaning their automated execution systematically amplifies tail risks.
Karmanpartap Singh Sidhu, Junyi Fan, Maryam Pishgar
Apr 14, 2026·q-fin.TR·PDF We utilize FinBERT, a domain-specific transformer model, to parse 6.5 million sentences from 16,428 S&P 500 quarterly earnings call transcripts (2015-2025) and demonstrate that post-earnings stock returns are not equally affected by all speakers in a conference call. Our section-weighted sentiment, with empirically derived speaker weights (Analyst 49%, CFO 30%, Executive 16%, Other 5%), achieves an out-of-sample Spearman IC of 0.142 versus 0.115 in-sample, generates monthly long-short alpha of 2.03% unexplained by the Fama-French five-factor model (t = 6.49), and remains significant after controlling for standardized unexpected earnings (SUE). FinBERT section-weighted sentiment entirely subsumes the Loughran-McDonald dictionary approach (FinBERT t = 5.90; LM t = 0.86 in the combined specification). Signal decay analysis and cumulative abnormal return charts confirm gradual price adjustment consistent with sluggish assimilation of soft information. All results undergo rigorous out-of-sample validation with an explicit temporal split, yielding improved rather than deteriorated predictive power.
Alessandro Falezza
Apr 13, 2026·q-fin.TR·PDF Battery energy storage systems (BESS) participating in multi-market electricity trading require price forecasts to optimize dispatch decisions. A widely held assumption is that forecast accuracy, measured by standard metrics such as mean absolute error (MAE), drives trading performance. We challenge this assumption using a hierarchical three-layer optimization system trading simultaneously on frequency containment reserve (FCR), automatic frequency restoration reserve (aFRR), day-ahead, and continuous intraday (XBID) markets in Germany and Switzerland over 2020-2025, with real market data from Regelleistung.net and Swissgrid. We find that rank correlation (Kendall tau), rather than MAE, is the primary predictor of intraday dispatch value: forecasts above an empirical threshold of tau approximately 0.85-0.95 capture up to 97-100% of perfect-foresight revenue, while persistence forecasts with near-zero tau capture only 33%. This threshold is stable across market regimes and volatility levels, and reflects the ordinal structure of the dispatch problem. Furthermore, under reserve market constraints, FCR capacity revenue exceeds XBID by 6.5x per MW, making capacity allocation -- not forecast accuracy -- the primary driver of total revenue. In the Swiss market, hydrological surplus anomalies are significantly associated with balancing market revenue (p = 0.0005), a mechanism absent from existing German-focused literature. These findings reframe forecast evaluation for BESS operators: the relevant question is not what the MAE is, but whether the forecast achieves tau-sufficiency.
Kun Liu, Liqun Chen
The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), frequently induce model sycophancy, while execution-based environments suffer from adversarial "Test Evasion" by unconstrained agents. In this paper, we introduce an objective alignment paradigm: \textbf{Out-of-Money Reinforcement Learning (OOM-RL)}. By deploying agents into the non-stationary, high-friction reality of live financial markets, we utilize critical capital depletion as an un-hackable negative gradient. Our longitudinal 20-month empirical study (July 2024 -- February 2026) chronicles the system's evolution from a high-turnover, sycophantic baseline to a robust, liquidity-aware architecture. We demonstrate that the undeniable ontological consequences of financial loss forced the MAS to abandon overfitted hallucinations in favor of the \textbf{Strict Test-Driven Agentic Workflow (STDAW)}, which enforces a Byzantine-inspired uni-directional state lock (RO-Lock) anchored to a deterministically verified $\geq 95\%$ code coverage constraint matrix. Our results show that while early iterations suffered severe execution decay, the final OOM-RL-aligned system achieved a stable equilibrium with an annualized Sharpe ratio of 2.06 in its mature phase. We conclude that substituting subjective human preference with rigorous economic penalties provides a robust methodology for aligning autonomous agents in high-stakes, real-world environments, laying the groundwork for generalized paradigms where computational billing acts as an objective physical constraint
Seongjin Kim, Jin Hyuk Choi
Apr 11, 2026·q-fin.TR·PDF We develop a multi-period Kyle-type model that incorporates both mandatory disclosure of informed trades and imperfect competition among market makers. We prove the existence and uniqueness of a linear equilibrium and show that the liquidity-enhancing effect of disclosure is fundamentally linked to the degree of market-making competition. Disclosure lowers trading costs by reducing price impact, and its marginal benefit is strictly larger when competition is weak. We empirically validate this prediction using the 2002 Sarbanes-Oxley Act disclosure reform as a natural experiment. A difference-in-differences analysis of U.S. equities confirms that the spread reduction following enhanced disclosure is significantly larger for stocks with fewer active market makers.
Shaw Dalen
Prediction markets are starting to look less like crowd polls and more like electronic markets. The central question is therefore no longer only whether these markets forecast well, but what happens when institutional liquidity enters: do spreads tighten, does price discovery improve, and do those gains actually reach the traders who are slowest to react when information arrives? This paper offers a research design for answering that question. It defines a broad market-quality lens, separates the main channels through which institutional liquidity enters, and maps the identification problems that arise in live venue data. It also uses a synthetic microstructure laboratory as a proof of concept for the measurement pipeline. The main lesson of the synthetic exercise is deliberately narrow. Market-maker coverage, liquidity incentives, and automation do not have to work through the same channel; average liquidity gains do not have to translate into equal gains for all traders; and the sharpest welfare losses are most likely to appear in shock states, when slower takers receive the least pass-through of tighter quoted markets. The synthetic results are useful because they stress-test the design, not because they settle the live empirical question.
Maxime Saxena, Marco Pangallo, Fabio Caccioli, R. Maria del Rio-Chanona
As Large Language Models (LLMs) become increasingly integrated into financial systems, understanding their behavioural properties is crucial. Do LLMs conform to the rational expectations paradigm, do they exhibit human-like "animal spirits", or do they instead manifest distinct "machine spirits"? We investigate these questions with a simulated financial market, exploring the behaviour of 15 LLMs spanning a range of sizes, capabilities, and providers. Our results show that LLMs exhibit a spectrum of economic behaviours, from stable coordination on the fundamental value to human-like speculative bubbles. These behaviours are generally inconsistent with the rational expectations hypothesis. We also consider an ecology of heterogeneous agents, a more realistic setting compared to markets with identical LLM agents. These mixed markets can produce outcomes which vary substantially across repeated simulations. Even the most advanced models fail to consistently stabilise the market, with price bubbles sometimes forming despite only a minority of agents naturally forming bubbles. Instead, advanced models in mixed markets adapt their forecasting strategies to the behaviour of other agents. This adaptation can allow them to successfully exploit less sophisticated counterparts and achieve higher profits, but can also contribute to increased market volatility. These findings suggest that the introduction of AI agents into financial markets fundamentally reshapes their ecology. In particular, heterogeneous populations of LLMs can generate endogenous instability, while individual-level adaptation may amplify, rather than mitigate, market volatility.
Rajat M. Barot, Arjun S. Borkhatariya
This paper presents PolySwarm, a novel multi-agent large language model (LLM) framework designed for real-time prediction market trading and latency arbitrage on decentralized platforms such as Polymarket. PolySwarm deploys a swarm of 50 diverse LLM personas that concurrently evaluate binary outcome markets, aggregating individual probability estimates through confidence-weighted Bayesian combination of swarm consensus with market-implied probabilities, and applying quarter-Kelly position sizing for risk-controlled execution. The system incorporates an information-theoretic market analysis engine using Kullback-Leibler (KL) divergence and Jensen-Shannon (JS) divergence to detect cross-market inefficiencies and negation pair mispricings. A latency arbitrage module exploits stale Polymarket prices by deriving CEX-implied probabilities from a log-normal pricing model and executing trades within the human reaction-time window. We provide a full architectural description, implementation details, and evaluation methodology using Brier scores, calibration analysis, and log-loss metrics benchmarked against human superforecaster performance. We further discuss open challenges including hallucination in agent pools, computational cost at scale, regulatory exposure, and feedback-loop risk, and outline five priority directions for future research. Experimental results demonstrate that swarm aggregation consistently outperforms single-model baselines in probability calibration on Polymarket prediction tasks.
Zhenyu Gao, Wenxi Jiang, Yutong Yan
Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We propose a supervised fine-tuning (SFT) approach that uses Low-Rank Adaptation (LoRA) to train off-the-shelf LLMs on instruction datasets constructed from rational benchmark forecasts. By intervening at the parameter level, SFT changes how LLMs map observed information into forecasts and thereby mitigates extrapolation bias. We evaluate the fine-tuned model in two settings: controlled forecasting experiments and cross-sectional stock return prediction. In both settings, fine-tuning corrects the extrapolative bias out-of-sample, establishing a low-cost and generalizable method for debiasing LLMs.
Ruichao Jiang, Long Wen
We extend AMM trade functions to negative inputs via the \textit{concave continuation}, derived from the invariance of the local conservation law under allocation direction flips. This unifies routing and arbitrage into a single problem. We extend the one-hop transfer algorithm proposed in \cite{jiang} to this setting.
Yun Zhao, Alex S. L. Tse, Harry Zheng
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 in which the stopping times are modeled by the jump times of Cox processes driven by bounded, non-randomized intensity controls. Under the exploratory formulation, the agent's randomized control is characterized via the probability measure over the jump intensities, and their objective function is regularized by Shannon's differential entropy. This yields a system of the exploratory HJB equations and Gibbs distributions in closed-form as the optimal policy. Error estimates and convergence of the RL objective to the value function of the original problem are established. Finally, an RL algorithm is designed, and its implementation is showcased in a pairs-trading application.
Kyungsub Lee
This paper presents a method for forecasting limit order book durations using a self-exciting flexible residual point process. High-frequency events in modern exchanges exhibit heavy-tailed interarrival times, posing a significant challenge for accurate prediction. The proposed approach incorporates the empirical distributional features of interarrival times while preserving the self-exciting and decay structure. This work also examines the stochastic stability of the process, which can be interpreted as a general state-space Markov chain. Under suitable conditions, the process is irreducible, aperiodic, positive Harris recurrent, and has a stationary distribution. An empirical study demonstrates that the model achieves strong predictive performance compared with several alternative approaches when forecasting durations in ultra-high-frequency trading data.
Philip Z. Maymin
Mar 31, 2026·q-fin.PR·PDF We derive the stochastic price process for tokens whose sole price discovery mechanism is a constant-product automated market maker (AMM). When the net flow into the pool follows a diffusion, the token price follows a constant elasticity of variance (CEV) process, nesting Black-Scholes as the limiting case of infinite liquidity. We obtain closed-form European option prices and introduce liquidity-adjusted Greeks. The CEV structure generates a leverage effect -- volatility rises as price falls -- whose normalized implied volatility skew depends only on the pool's weighting parameter, not on pool depth: Black-Scholes underprices 20%-out-of-the-money puts by roughly 6% in implied volatility terms at every pool depth, while the absolute pricing discrepancy vanishes as pools deepen. Empirically, after controlling for pool depth and flow volatility, realized return variance across 90 Bittensor subnets exhibits a strongly negative price elasticity, decisively rejecting geometric Brownian motion and consistent with the CEV prediction. A complementary delta-hedged backtest across 82 subnets confirms near-identical hedging errors at the money, consistent with the prediction that pricing differences are concentrated in the wings.
Thomas P. McAuliffe, Samuel Liew, Yuchao Li, Andrey Ushenin, Chihang Wang, Alexandros Tasos, Jack Pearce, Dimitris Tasoulis, Dimitri P. Bertsekas, Theodoros Tsagaris
Mar 30, 2026·q-fin.TR·PDF We address the problem of executing large client orders in continuous double-auction markets under time and liquidity constraints. We propose a model predictive control (MPC) framework that balances three competing objectives: order completion, market impact, and opportunity cost. Our algorithm is guided by a trading schedule (such as time-weighted average price or volume-weighted average price) but allows for deviations to reduce the expected execution cost, with due regard to risk. Our MPC algorithm executes the order progressively, and at each decision step it solves a fast quadratic program that trades off expected transaction cost against schedule deviation, while incorporating a residual cost term derived from a simple base policy. Approximate schedule adherence is maintained through explicit bounds, while variance constraints on deviation provide direct risk control. The resulting system is modular, data-driven, and suitable for deployment in production trading infrastructure. Using six months of NASDAQ 'level 3' data and simulated orders, we show that our MPC approach reduces schedule shortfall by approximately 40-50% relative to spread-crossing benchmarks and achieves significant reductions in slippage. Moreover, augmenting the base policy with predictive price information further enhances performance, highlighting the framework's flexibility for integration with forecasting components.
Yixin Cao, Xianfeng Cheng, Yijie Liu
Transfer-based anti-money laundering (AML) systems monitor token flows through transaction-graph abstractions, implicitly assuming that economically meaningful value migration is sufficiently encoded in transfer-layer connectivity. In this paper, we demonstrate that this assumption, the bedrock of current industrial forensics, fundamentally collapses in composable smart-contract ecosystems. We formalize two structural mechanisms that undermine the completeness of transfer-layer attribution. First, we introduce Principal-Execution-Beneficiary (PEB) separation, where intent originators, transaction executors (e.g., MEV searchers), and ultimate beneficiaries are functionally decoupled. Second, we formalize state-mediated value migration, where economic coupling is enforced through invariant-driven contract state transitions (e.g., AMM reserve rebalancing) rather than explicit transfer continuity. Through a real-world case study of role-separated limit order execution and a constructive cross-pool arbitrage model, we prove that these mechanisms render transfer-layer observation neither attribution-complete nor causally closed. We further argue that simply expanding transfer-layer tracing capabilities fails to resolve the underlying attribution ambiguity inherent in structurally decoupled execution. Under modular composition and open participation markets, these mechanisms are structurally generative, implying that heuristic-based flow tracing has reached a formal observational boundary. We advocate for a paradigm shift toward AML based on execution semantics, focusing on the restitution of economic causality from atomic execution logic and state invariants rather than static graph connectivity.
Patrick Noble, Mathieu Rosenbaum, Saad Souilmi
Mar 25, 2026·q-fin.TR·PDF We introduce a practical, interactive simulator of the limit order book for large-tick assets, designed to produce realistic execution, costs, and P&L. The book state is projected onto a tractable representation based on spread and volume imbalance, enabling robust estimation from market data. Event timing is calibrated to reproduce the fine-scale temporal structure of real markets, revealing a pronounced mode at exchange round-trip latency consistent with simultaneous reactions and latency races among participants. We further incorporate a feedback mechanism that accumulates signed trade flow through a power-law decay kernel, reproducing both concave market impact during execution and partial post-trade reversion. Across several stocks and strategy case studies, the simulator yields realistic behavior where profitability becomes highly sensitive to execution parameters. We present the approach as a practical recipe: project, estimate, validate, adapt, for building realistic limit order book simulations.