Quant Letter
The week in quantitative finance research: 90 papers from arXiv, SSRN and RePEc, screened and ranked, 3–9 Oct 2026.
This week centers on AI systemic risk, factor discovery limits, and monetary transmission channels. Agentic AI systems create non-diversifiable contagion floors despite fleet size; automated factor mining shows no paradigm dominates; and Fed policy transmits primarily through risk appetite shifts rather than rates. See "Agentic AI and Systemic Risk," "FactorBench," and "Risk Appetite and Monetary Transmission."
If you read five papers this week, read these.
The study shows that agentic AI systems sharing a foundation model create non-diversifiable common exposure whose systemic risk floor does not shrink as the fleet grows, shifting concern from individual model risk to population-level contagion.
Surveys fifty years of quantitative investing as a history of changing implementation boundaries from diversification through machine learning, emphasizing alpha decay and the gap between research and production systems.
An autonomous agent evolved 940 factors over 17 days and finds that reusing backtest data inflates edge by a quarter to a third and in-sample improvement predicts worse performance.
Topics drawing unusually many papers this week.
4.6% of this week's 776 new papers, 1.8x its share over the previous 2 weeks (2.6%).
4.4% of this week's 776 new papers, 1.6x its share over the previous 2 weeks (2.8%).
2.6% of this week's 776 new papers, 1.5x its share over the previous 2 weeks (1.8%).
What the quant community starred on GitHub this week, from a panel of 10,589 developers who follow financial machine learning (271 of the 860 we checked starred something). Counts only: we never publish who starred what.
AI trading agent executing trades on Monad blockchain.
★ 2,912+167 this weekTypeScriptNew repo
Autonomous financial deep research framework.
★ 196+8 this weekPythonNew repo
AI stock monitoring for A-shares, HK and US markets.
★ 2,047+104 this weekPython
Reverse engineer apps and binaries using AI agents.
★ 37.0k+36.6k this weekTypeScript
Open-source Rust reimplementation of Adobe Photoshop.
★ 32.1k+32.0k this weekRustNew repo
Mathematics library in Lean.
★ 12.8k+12.8k this weekLeanNew repo
Run Qwen3.8-Flash on consumer hardware with local APIs.
★ 19.2k+12.3k this weekC++New repo
End-to-end testing framework for web and mobile apps.
★ 8,332+6,418 this weekTypeScriptNew repo
Tool for porting PS5 executables to Linux and Windows.
★ 19.6k+16.6k this weekC++New repo
Now published in Journal of Economic Behavior & Organization · featured 8 Jan 2025; 4 citations
Passed 50 citations · featured 7 Feb 2024, 6 days after release
Passed 25 citations · featured 10 Apr 2024, 3 days after release
Filter by venue, topic or fanfare.
No papers match these filters.
Quantitative finance and ML-for-finance preprints
30 papers · 30 figures
The study shows that agentic AI systems sharing a foundation model create non-diversifiable common exposure whose systemic risk floor does not shrink as the fleet grows, shifting concern from individual model risk to population-level contagion.
Fanfare 4Risk, Credit & BankingSriram Nagaraj and Seung Jung LeePDF
A model-agnostic framework distills ranking priors from experts or teacher models into credit scorers via KL divergence, improving cold-start performance with scarce labeled data.
Fanfare 3Risk, Credit & BankingQiye Lu et al.PDF
Fitting separate dependence matrices to lower-tail, central, and upper-tail regimes reveals tail-driven co-movements that single Gaussian-copula structures systematically miss.
Fanfare 2Risk, Credit & BankingKatherine B. Ensor et al.PDF
A portfolio-aware benchmark comparing five thousand factors from nine automated mining methods across five equity markets finds that no discovery paradigm consistently dominates in signal quality or portfolio performance.
Fanfare 4Asset Pricing & FactorsZhuohan Wang and Carmine VentrePDF
Introduces a hierarchical discrete diffusion framework that generates pools of formulaic alphas by reconstructing complete candidate pools under current context and maximizing joint predictive performance and inner diversity.
Fanfare 3Asset Pricing & FactorsYanzheng Jin et al.PDF
An injected-truth protocol reveals that statistical admission gates eliminate false discoveries in weak-signal regimes but cut adoption rates to 1–7 percent, while criteria computed on absolute rather than excess returns reject all candidates.
Fanfare 3Asset Pricing & FactorsTianlun ZhengPDF
Decomposing earnings press releases and conference calls into shared and unique textual components shows that unique call content predicts returns better than repeated material.
Fanfare 3Asset Pricing & FactorsYuntao Wu et al.PDF
The study introduces a trillion-observation U.S. equity dataset and systematically evaluates 18 representation-learning methods across nearly two decades, finding that encoders with similar predictive performance organize market state very differently.
Fanfare 4ML & AI MethodsHumzah Merchant et al.PDF
A joint-embedding framework learns predictable incremental revisions from market data relative to a financial prior, combining interpretability from classic models with the pattern-capture strength of deep learning.
Fanfare 3ML & AI MethodsYizhi Luo et al.PDF
A benchmark evaluates frontier LLMs as live trading agents and finds that realized returns often diverge from capability-specific measurements, revealing outcome-capability gaps through decision traces.
Fanfare 3ML & AI MethodsJun Zhao et al.PDF
Proposes that large-language-model-driven trading agents delegated to autonomous execution define a nascent asset class, mapping infrastructure layers and projecting potential trillions in assets by 2030.
Fanfare 3ML & AI MethodsAmandeep SinghPDF
Proposes an LLM-guided framework for trading strategy refinement using accumulated experience and cross-period robustness, achieving 27.99% annualized return on Chinese equities with 1.63 Sharpe ratio.
Fanfare 3ML & AI MethodsChaoqun Yang et al.PDF
Fuses SEC financials with EPA emissions data and conformal machine learning to quantify divergence between self-reported and physical emissions, finding algorithmic divergence predicts lower valuation and profitability.
Fanfare 3ML & AI MethodsSourav Bose and Taoufik BouraouiPDF
When financial facts are withdrawn from prompts, identity attributes explain 96% of variation in equity allocation advice from a language model, replacing missing evidence.
Fanfare 4LLMs & TextSaanvi Khetan and Sankar BalasubramanianPDF
Introduces a benchmark that compares LLM-generated trading code to reference strategies bar by bar on identical data, revealing silent failures in implementation despite passing functional tests.
Fanfare 3LLMs & TextSiyu Wang et al.PDF
Separating risk-neutral shortfall probability from conditional severity in option prices shows that severity accounts for 91.5 percent of recession log premium movements, supplying joint empirical restrictions on uncertainty and economic activity.
Fanfare 3Derivatives & VolatilityTodd B. WalkerPDF
WRAP combines Wasserstein reweighting and optimal-transport perturbations in a distributionally robust framework to make deep hedging policies robust to nonstationarity and distributional drift in market conditions.
Fanfare 3Derivatives & VolatilityPhilipp J. Schneider et al.PDF
Replaces transformers with selective state space encoders in a hierarchical architecture for realized volatility forecasting, reducing error to 0.1927 on the Optiver benchmark with 33 percent fewer parameters than the attention variant.
Fanfare 2Derivatives & VolatilityMihai Bogdan Deaconu and Ioan Daniel PopPDF
MBOFormer and MBOFusion, two causal transformers with under 70 kilobyte serialized state, predict limit order book price trends with sub-millisecond latency across three markets and four prediction horizons.
Fanfare 3Trading, Microstructure & ExecutionDavid Schaurecker et al.PDF
Analysis of high-frequency limit-order-book geometry finds market states form a continuous structure with a dominant latent coordinate capturing between 83.66% and 85.27% of covariance variation.
Fanfare 3Trading, Microstructure & ExecutionAnjali ThawaitPDF
Varying execution realism from ideal fills to latency and impact reshuffles rankings of LLM and classical trading policies, showing how backtest conventions affect headline results.
Fanfare 3Trading, Microstructure & ExecutionWeicheng XuePDF
A regime-switching Hawkes process models intraday electricity order flow across liquidity conditions, showing that stress mainly strengthens self-excitation rather than reshaping cross-side dynamics.
Fanfare 2Trading, Microstructure & ExecutionAyoub Jhabli et al.PDF
Tiny neuroevolved recurrent networks rank first on both forecast accuracy and daily long-short returns across four portfolios, outperforming larger transformers and proving that forecast accuracy does not guarantee trading profit.
Fanfare 3Portfolio & AllocationJonathan Chang and Zimeng LyuPDF
Proposes a portfolio rule that simultaneously selects class and estimates weights to minimize expected utility regret, attaining both minimax and Bayes lower bounds without requiring prior information.
Fanfare 3Portfolio & AllocationMasahiro KatoPDF
MemTrial uses factorial design to isolate what each memory contributes to portfolio decisions by crediting experiences with their marginal effect rather than shared market moves.
Fanfare 3Portfolio & AllocationGuanghao Wu et al.PDF
A method represents epistemic uncertainty with credal sets and combines them with a decision rule that avoids catastrophic predictions under conditional value-at-risk minimization.
Fanfare 3Portfolio & AllocationTimo Löhr et al.PDF
Derives a closed-form expression for worst-case conditional value-at-risk under reward-penalty mechanisms and distribution uncertainty, enabling optimal portfolio allocations that balance losses with downside risk.
Fanfare 2Portfolio & AllocationJun Cai et al.PDF
A framework characterizes optimal investment policies for reaching financial goals by deadline, revealing that policies can decrease in asset drift and need not converge to risk-free allocation.
Fanfare 2Portfolio & AllocationGechun Liang et al.PDF
Robust optimization models minimize worst-case loss and downside risk for enhanced indexing under distributional uncertainty, beating benchmarks and standard robust approaches in out-of-sample wealth.
Fanfare 2Portfolio & AllocationJun Cai and Zhiqiao SongPDF
A convex method learns causal filters that balance stationarity and input preservation for financial time series, adapting filtering strength to persistence while preserving signal similarity.
Fanfare 2Econometrics & ForecastingLorena Egger and Mathis LingerPDF
New working papers in finance, economics and ML
30 papers
Surveys fifty years of quantitative investing as a history of changing implementation boundaries from diversification through machine learning, emphasizing alpha decay and the gap between research and production systems.
Fanfare 4Portfolio & AllocationXuan Feng et al.
Analyzing 100 years of daily data, the study finds volatility scaling harmed returns before 1985 but improved them after, a shift attributed to derivatives markets and deregulation, with walk-forward Sharpe ratio of 1.01.
Fanfare 4Portfolio & AllocationSparsh Patel
Eleven systematic strategies across equities, futures, and currencies achieve a 1.91 Sharpe ratio net of costs from January 2012 to June 2026, with 23.6% compound annual return.
Fanfare 4Portfolio & AllocationOliver Navarro
An autonomous agent evolved 940 factors over 17 days and finds that reusing backtest data inflates edge by a quarter to a third and in-sample improvement predicts worse performance.
Fanfare 4ML & AI MethodsKamer Ali Yuksel
A natural-language analysis of 13,757 firms finds AI exposure surged after ChatGPT and predicts 1.37 percent higher annual returns, though the effect is concentrated after the launch and driven by firm-specific factors.
Fanfare 4ML & AI MethodsSakshi Basu et al.
An autonomous research loop in which agents propose factor candidates and code verifies them builds multi-factor alpha models, screening 212 predictors and admitting 14 that raise baseline information coefficient out-of-sample.
Fanfare 3ML & AI MethodsErfan Sadeghi
GFlowAlpha uses neuro-symbolic search and internalizes econometric quality control as online rewards to mine white-box factors, delivering mean out-of-sample daily ICIR of 0.485 with Fama-MacBeth t-statistics of 4.99 on Chinese stocks.
Fanfare 3ML & AI MethodsHongwei Yue et al.
The research proves that query-counted Deflated Sharpe Ratios certify noise in adaptive research and proposes sealed-holdout verification, where validity depends on bits revealed rather than strategy count.
Fanfare 3ML & AI MethodsShlok Singh Sobti
A graph neural network combining temporal and cross-asset volatility patterns reduces mean squared error and quasi-likelihood loss by approximately 9.9% and 3.4% on Dow stocks.
Fanfare 3ML & AI MethodsJongu Lee et al.
The study decomposes Federal Reserve announcements into three orthogonal shocks and traces each through the equity cross-section, finding rate-path surprises dominate while standard balance-sheet characteristics carry no additional power beyond beta and size.
Fanfare 4Asset Pricing & FactorsPablo De Diego Leguina
A two-country model attributes 251 basis points of U.S. equity premium gains and 71 basis points of global rate decline since 1980 to demographic aging.
Fanfare 4Asset Pricing & FactorsChristopher Hyland and Tim Willems
Constructs a characteristics-based systematic risk measure using rate jumps that predicts out-of-sample corporate bond returns, with high-minus-low decile portfolio earning 9.12% annually and 7.80% alpha.
Fanfare 3Asset Pricing & FactorsYongfu Feng et al.
The study shows that high-conviction beliefs exert outsized influence on prices, with a long-short portfolio exploiting conviction-weighted disagreement earning 13.2 percent annualized six-factor alpha.
Fanfare 3Asset Pricing & FactorsChristian Goulding et al.
The study measures AI exposure across 284 U.S. firms and finds that an AI-factor explains only 18% variance alongside conventional factors, suggesting AI is a distinct cross-industry risk lens separate from traditional spillovers.
Fanfare 3Asset Pricing & FactorsVamsidhar Ambatipudi
Asset prices respond to monetary policy uncertainty around FOMC announcements; a New Keynesian model shows policy risk accounts for much of equity and inflation-bond risk premia and weakens activity when elevated.
Fanfare 4Macro-Finance & RatesCorey Feldman and Thomas King
U.S. monetary tightening raises term premia sharply in pegged economies but not floating ones; a DSGE model shows pegs force adjustment through domestic rates, tightening leverage constraints and amplifying spillovers.
Fanfare 3Macro-Finance & RatesPawan Gopalakrishnan and Ankit Kumar
A measure of cross-country geopolitical risk skewness predicts U.S. Treasury risk premia out-of-sample and forecasts weaker activity, adding incremental value beyond yield curves and standard macroeconomic predictors.
Fanfare 3Macro-Finance & RatesFuwei Jiang et al.
Optimal rate-setting creates time-inconsistency: market expectations become too sensitive to policy surprises, amplifying real effects of central bank forecast errors; less aggressive rules cut output volatility.
Fanfare 3Macro-Finance & RatesVicente Jimenez-Gimpel and Tomás Caravello
Applies a strict pre-registered protocol to eleven trading signals across equity and futures markets, finding only trend survives development and hold-out periods with borderline significance after multiple-testing adjustment.
Fanfare 3Trading, Microstructure & ExecutionYasanji Ratnaike
Well-documented Indian equity anomalies replicate strongly in-sample but all fail to survive 12 to 32 basis point retail transaction costs; required directional accuracy reaches 72% at hourly horizons.
Fanfare 3Trading, Microstructure & ExecutionKarthikeya Voocha
The study shows that Baa-Aaa spreads at 27-year maturity test pricing kernels better than shorter maturities, with a structural refinancing model matching observed spreads while prior kernels overpredict by 27 to 68 basis points.
Fanfare 3Derivatives & VolatilitySöhnke M. Bartram et al.
A reinforcement learning method embedding Black-Scholes delta guidance cuts hedging error by 19-38% across simulated and real options data with robust statistical significance.
Fanfare 3Derivatives & VolatilitySparsh Patel
Shows that large-language-model scores of default risk from earnings calls predict bond rating migration one year ahead where analysts disagreed, capturing information not yet priced in spreads.
Fanfare 2LLMs & TextMoazzam Khoja
The study constructs a geoeconomic fear index from news articles and finds that higher fear predicts wider emerging-market sovereign spreads, especially for speculative-grade issuers.
Fanfare 3LLMs & TextHui Ding et al.
Revenue surprises on 95 DeFi protocols predict abnormal token returns, with one-standard-deviation surprises associated with 28.8 basis points higher returns over three days when tokens have direct revenue claims.
Fanfare 3Crypto & DeFiSimon Harre et al.
The study forecasts time-varying return spillovers among cryptocurrencies using machine learning, finding monetary policy and funding rates drive connectedness and classifying events that shift spillover composition into contagion types.
Fanfare 3Crypto & DeFiEric Osmer et al.
The research shows that after U.S. Bitcoin ETF approval in January 2024, return and volatility linkages between Bitcoin and equities strengthened substantially, with volatility spillovers becoming markedly asymmetric from stocks to crypto.
Fanfare 3Crypto & DeFiYat Ming Eddie Lam
A causal framework compares six estimators of treatment effect to optimally assign debt restructuring interventions, revealing that targeting borrowers by predicted effect generates substantially positive value where blanket treatment fails.
Fanfare 3Risk, Credit & BankingAntonio Aguilera Gonzalez
Using Portuguese wildfire data, the research finds firms whose banks also lend to suppliers experience 10 percentage points smaller credit declines and face attenuated real losses.
Fanfare 3Risk, Credit & BankingMiguel Almeida Ferreira and Antonio R. dos Santos
A global study of 357,630 firm-years shows firms with more short-term debt cut capital expenditure by 2.156 percentage points, mainly due to refinancing availability constraints.
Fanfare 3Corporate FinanceMirza Muhammad Naseer et al.
Working papers curated by RePEc's NEP field reports
30 papers · 22 figures
The research shows Fed policy affects risk asset prices primarily through risk appetite shifts, not interest rates; transmission via risk appetite dwarfs rate-channel effects.
Fanfare 4Asset Pricing & FactorsMichael D. Bauer et al.PDF
The paper proves that asset pricing models solving equity and risk-free rate puzzles fail to generate observed interest-rate differentials between risky and safe currencies.
Fanfare 3Asset Pricing & FactorsTarek Alexander Hassan et al.PDF
Inferring expected returns from stock prices and cash flows reveals an upward-sloping equity term structure, but value and speculative-grade firms show flat or downward slopes.
Fanfare 3Asset Pricing & FactorsLieven Baele et al.PDF
A quantified general-equilibrium model of 23,000 firms across 48 countries shows financial and trade liberalization concentrate activity in largest firms with larger gains for emerging economies.
Fanfare 3Asset Pricing & FactorsLoukas Karabarbounis et al.PDF
A demand-system framework quantifies that $100 billion in Treasury supply raises five-year yields by roughly 3 basis points, with effects driven by changing foreign and hedge-fund participation.
Fanfare 3Macro-Finance & RatesDaniel O. Beltran and Canlin LiPDF
A model shows U.S. Treasury collateral advantage drives dollar appreciation during stress and reconciles exorbitant privilege, financial intermediation, and convenience yield perspectives.
Fanfare 3Macro-Finance & RatesMichael B. Devereux et al.PDF
Rate cuts initially reduce wealth inequality but increase it medium-term; housing drives effects at the bottom while equities drive them at the top.
Fanfare 3Macro-Finance & RatesAlessandro Franconi and Giacomo RellaPDF
A model with time-varying skewness in cost-push shocks generates persistent stagflationary effects; optimal policy leans against the balance of inflation risks.
Fanfare 2Macro-Finance & RatesAndrea De Polis et al.PDF
A DSGE model reveals energy and exchange-rate shocks drive euro inflation volatility, and optimal policy can exploit the exchange-rate channel rather than looking through energy shocks.
Fanfare 2Macro-Finance & RatesAlice Albonico et al.PDF
US monetary tightening attracted capital through Eurodollar borrowing but did not transmit to foreign output, revealing continued financial segmentation despite offshore growth.
Fanfare 2Macro-Finance & RatesGuillaume Bazot et al.PDF
Dollar safe asset convenience yields remain stable domestically since 2019 but decline globally relative to other currencies, with repo markets leading.
Fanfare 2Macro-Finance & RatesArvind Krishnamurthy and Miguel ChumboPDF
Volatility and kurtosis reveal that dollar depreciation and rising Treasury yields reflect multiple distinct shocks rather than a single tariff announcement shock.
Fanfare 2Macro-Finance & RatesLucas ter Steege and Sofia VelascoPDF
An index capturing structural financial weaknesses displays gradual buildup before crises, predicts shock amplification, and reveals delayed monetary policy transmission effects.
Fanfare 3Risk, Credit & BankingMichele Modugno et al.PDF
UK firm-level data shows relaxing credit frictions raises output by 25% and wages by 23%, with most gains from capital accumulation rather than reallocation.
Fanfare 3Risk, Credit & BankingTimothy J. Besley et al.PDF
The ECB's "whatever it takes" announcement reversed euro area banks' risk appetite, reducing loan growth and credit risk, showing capitalization can curb lending during crises.
Fanfare 3Risk, Credit & BankingCarlo Alcaraz et al.PDF
Improved job opportunities for bankers increase non-investment-grade lending and borrower risk without compensating spreads, raising systemic risk through weakened workplace discipline.
Fanfare 3Risk, Credit & BankingValentin Kecht and Georg SchneiderPDF
The study shows that mutual fund managers' policy beliefs predict market returns and explain positive alphas, while sentiment beliefs attract flows but lack predictive power.
Fanfare 3Portfolio & AllocationZhenyu Gao et al.PDF
Extending Campbell et al., the analysis shows empirically measured deviations from interest parity reverse optimal currency demands for emerging-market investors.
Fanfare 2Portfolio & AllocationLuis M. Viceira and Sally ShenPDF
A framework using deviations from interest-rate parity identifies when exchange-rate movements stem from financial shocks rather than fundamentals, aiding intervention decisions.
Fanfare 3Econometrics & ForecastingEce Ozge Emeksiz et al.PDF
The sequencing and emphasis of sentiment within central bank statements predict rate decisions and inflation expectations beyond average tone alone.
Fanfare 3Econometrics & ForecastingMartin Feldkircher et al.PDF
Fractional processes outperform discrete models like HAR for forecasting realized volatility at longer horizons by better balancing recent levels against long-run persistence.
Fanfare 2Econometrics & ForecastingShuping Shi et al.PDF
CLONE decomposes daily price moves into demand, productivity, inflation, and policy news using stocks, bonds, and inflation swaps; aggregate demand dominated until 2021.
Fanfare 2Econometrics & ForecastingBruno Feunou et al.PDF
Treasury yield curve slope volatility forecasts industrial production and employment growth at medium and long horizons, outperforming term spread alone after the 2008 crisis.
Fanfare 2Econometrics & ForecastingAnastasios Megaritis et al.PDF
A Bayesian spike-and-slab method improves high-dimensional panel VAR forecasting and reveals heterogeneous spillover structures in sovereign bonds and macro data.
Fanfare 2Econometrics & ForecastingZhiruo Zhang et al.PDF
A time-varying VAR network reveals supply-inelastic coastal markets absorb largest regulatory shocks and spillovers persist to monetary conditions and inflation expectations.
Fanfare 2Econometrics & ForecastingOnur Polat et al.PDF
Time-varying beliefs about the central bank's reaction function collapsed at the zero bound and rose only after observed tightening, not from guidance alone.
Fanfare 2Econometrics & ForecastingJonathan Hambur and Qazi HaquePDF
Granular blockchain data reveals the Terra crash resulted from subsidized money creation, real-time transaction visibility, and investor concentration amplifying financial fragility.
Fanfare 3Crypto & DeFiJiageng Liu et al.PDF
The study finds that US risk-free rates predict stablecoin lending rates in decentralized finance, though transmission operates mainly through crypto-native factors like utilization.
Fanfare 2Crypto & DeFiGrigoriy KorolevPDF
Industries with higher AI intensity show significantly higher returns and valuations when hit by supply and technology shocks but not demand shocks.
Fanfare 3ML & AI MethodsChristina Anderl and Guglielmo Maria CaporalePDF
Cross-sectional dispersion in volatility forecasts predicts delta-hedged straddle losses of 5.14% per month, consistent with mispricing rather than risk compensation.
Fanfare 3Derivatives & VolatilityTuran G. Bali et al.PDF
