{"paper_id":"2510.10807","title":"Multi-Agent Regime-Conditioned Diffusion (MARCD) for CVaR-Constrained Portfolio Decisions","authors":["Ali Atiah Alzahrani"],"paper_date":"2025-10-12","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.10807v3","page_url":"https://thequant.space/flowcharts/multi-agent-regime-conditioned-diffusion-marcd-for-cvar-co/","scores":{"empirical_rigor":8.5,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes MARCD, a regime‑conditioned generative‑to‑decision pipeline that combines a Gaussian HMM, a diffusion scenario generator, blended moment extraction, and a CVaR epigraph quadratic program for portfolio allocation.","quote":"We present MARCD, a generative-to-decision framework with: (i) a Gaussian HMM to infer latent regimes; (ii) a diffusion generator that produces regime-conditioned scenarios; (iii) signal extraction via blended, shrunk moments; and (iv) a governed CVaR epigraph QP.","summary":"We examine whether regime-conditioned generative scenarios combined with a convex CVaR allocator improve portfolio decisions under regime shifts. We present MARCD, a generative-to-decision framework with: (i) a Gaussian HMM to infer latent regimes; (ii) a diffusion generator that produces…","strategy":"MARCD"},"assumptions":{"status":"available","items":[{"assumption":"Monthly rebalancing on the last trading day with a fixed 10 bps transaction cost per trade.","type":"execution","stated":"explicit","quote":"All strategies (EW, RP, BL, MARCD) rebalance monthly on the last trading day, incur identical transaction costs of 10 bps per trade, and are subject to the same turnover controls"},{"assumption":"Turnover is limited by an ℓ1 cap of 0.20 on weight changes.","type":"execution","stated":"explicit","quote":"an ℓ1 cap ∥wt−wt−1∥1 ≤0.20; no penalty, κ=0, unless stated otherwise"},{"assumption":"The latent regime process follows a Gaussian Hidden Markov Model with a 3‑year rolling estimation window.","type":"model","stated":"explicit","quote":"Protocol. Strict walk-forward; HMM 3y rolling; scenarios conditioned on zt"},{"assumption":"The asset universe consists of ten liquid ETFs with daily total returns from Yahoo Finance Adjusted Close (including dividends).","type":"data","stated":"explicit","quote":"Data. Daily total returns computed from Yahoo Finance Adjusted Close (dividends included)"},{"assumption":"The CVaR allocator uses an epigraph quadratic program with Lipschitz solution map and decision‑regret bounds.","type":"model","stated":"explicit","quote":"The CVaR epigraph QP (Sec. 3.4) has a Lipschitz solution map in (µ, Σ) and admits a decision-regret bound under moment and CVaR perturbations"},{"assumption":"Scenario diagnostics (KS, ES, VS, VaR, CVaR) are evaluated on the same monthly‑rebalanced, cost‑adjusted returns.","type":"statistical","stated":"explicit","quote":"Diagnostics. KS, ES, VS; LB p(|r|); VaR0.95 unconditional coverage (Kupiec UC) p; CVaR0.95 error ( bps)."}]},"datasets":{"status":"available","items":[{"name":"Ten liquid multi‑asset ETFs","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2005‑2025","universe":"10 liquid ETFs","quote":"Data. Daily total returns computed from Yahoo Finance Adjusted Close (dividends included)","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Daily total returns computed from Yahoo Finance Adjusted Close (dividends included). Baselines.","mentions":1,"used_in":1}],"sample":{"start":"2020","end":"2025","market":"liquid multi-asset ETFs","asset_class":"multi-asset","frequency":"monthly"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A flat 10 bps cost per trade is applied to all strategies and included in reported performance.","quote":"All strategies (EW, RP, BL, MARCD) rebalance monthly on the last trading day, incur identical transaction costs of 10 bps per trade","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat 10 bps cost per trade is applied to all strategies and included in reported performance.","card_quote":"All strategies (EW, RP, BL, MARCD) rebalance monthly on the last trading day, incur identical transaction costs of 10 bps per trade","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"MARCD achieves a MaxDD of 9.3 % versus 14.1 % for the benchmark (BL), a 34 % reduction in drawdown over the 2020‑2025 out‑of‑sample period.","kind":"performance","quote":"Over 2020–2025 OOS, MaxDD is 9.3% for MARCD vs BL 14.1% and EW 21.2% (34%/56% lower; absolute 4.8%/11.9%)"},{"finding":"MARCD’s Sharpe ratio is 1.23, compared with 1.02 for BL and 0.72 for EW, indicating higher risk‑adjusted returns.","kind":"performance","quote":"Performance— MARCD attains higher risk-adjusted performance (Sharpe 1.23 vs. 1.02 for BL)"},{"finding":"The Calmar ratio improves to 1.11 for MARCD versus 0.70 for BL, reflecting better peak‑to‑trough behavior.","kind":"performance","quote":"Consistent with this, Calmar improves to 1.11 (BL 0.70; EW 0.38)"},{"finding":"In ablation studies, removing regime conditioning or the CVaR term raises MaxDD to 11.3 % and 14.6 % respectively, and reduces Sharpe to around 1.12‑1.13.","kind":"performance","quote":"Removing either regime conditioning or the CVaR term weakens tail control"},{"finding":"Scenario diagnostics show MARCD has the lowest KS, ES, VS and CVaR error among baselines (KS 0.154, ES 0.289, VS 0.247, CVaR0.95 err 15 bps).","kind":"statistical","quote":"MARCD 0.154 0.289 0.247 0.50 0.58 15"}],"reported_performance":{"strategy":"MARCD","sharpe":1.23,"sharpe_benchmark":1.02,"annual_return_pct":10.3,"total_return_pct":null,"max_drawdown_pct":9.3},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":87,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:24:55Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}