Paper: arXiv 2611.19937
Authors: Annan Wang, Yuchen Xie, Yu Cen, Leon Liangyu Chen, Qianyu Julie Zhu, Xin Li, Tianyi Wei, Weisi Lin
Abstract
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 forecasting from portfolio construction, potentially misaligning learning with allocation and execution objectives. We present AllocFlow, an end-to-end flow-matching framework that directly generates joint portfolio allocations from raw multi-asset market histories. To capture dependencies among portfolio positions, AllocFlow employs a cross-asset flow Transformer conditioned on temporal market representations to generate continuous, signed position weights across all instruments jointly. To address the sample inefficiency and instability of learning continuous allocation policies from scratch, we establish a two-stage training scheme: strategy-supervised imitation shapes a structured distribution of candidate portfolios, followed by group-relative reinforcement learning (RL) that refines joint decisions using portfolio-level financial rewards and a frozen policy reference. On hourly cryptocurrency perpetual futures, RL refinement raises the annualized net return of the imitation policy from \(27.79\%\) to \(51.38\%\) and its Calmar ratio from \(0.955\) to \(4.043\), surpassing the teacher strategy on every metric, and AllocFlow reaches a Calmar ratio of \(4.90\) on six further months of unseen 2026 data without retraining.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper introduces a novel end-to-end flow-matching framework for portfolio allocation, combining imitation learning and reinforcement learning. It demonstrates strong empirical results on cryptocurrency perpetual futures with robust backtesting and out-of-sample performance. The methodology is well-articulated, though some mathematical derivations could be more explicit in the excerpt.
Research Flowchart
flowchart TD
A["Research Goal: End-to-End Joint Portfolio Allocation from Raw Market Data"] --> B{"Key Methodology: AllocFlow Framework"};
B --> C["Stage 1: Strategy-Supervised Imitation Learning"];
C --> D["Stage 2: Group-Relative Reinforcement Learning (RL)"];
B -- Computational Processes --> E["Cross-Asset Flow Transformer + Flow-Matching"];
A -- Data/Inputs --> F["Raw Multi-Asset Market Histories (e.g., Hourly Crypto Perpetual Futures)"];
D & F --> G["Key Findings: Significant Performance Improvement"];
G -- Outcomes --> H["Annualized Net Return: 27.79% (Imitation) -> 51.38% (RL); Calmar Ratio: 0.955 (Imitation) -> 4.043 (RL); 4.90 Calmar on unseen 2026 data"];
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes AllocFlow, an end‑to‑end cross‑asset flow‑matching Transformer that generates joint continuous signed portfolio allocations directly from raw multi‑asset market histories.
Source sentence
We present AllocFlow, an end-to-end flow-matching framework that directly generates joint portfolio allocations from raw multi-asset market histories.
Assumes 6
- Trading is performed on hourly cryptocurrency perpetual futures with a flat 5 bps fee per unit of absolute traded weight. execution
Source sentence
Orders are changes from current to target weights, including entries and exits when the eligible list changes, and incur 5 basis points (bps, 0.01%) per unit of absolute traded weight. This fee is the maximum of the base-tier taker fees of major perpetual-futures venues and the fees in prior crypto trading papers, and the median half-spread of the traded contracts is only 0.24 bps (Appendix C.3).
- The eligible asset universe is reconstituted weekly as the 20 assets with highest cumulative trading volume over the prior 60 days. market
Source sentence
Every week, the eligible list is recomputed as the 20 assets with the highest cumulative trading volume in the preceding 60 days. This causal reconstitution tests a changing opportunity set rather than a list selected with knowledge of the full test period.
- The Kronos encoder is frozen after pre‑training that ends in June 2024 and contains no information from the test period. model
Source sentence
Kronos pretraining ends in June 2024 [46], before the hourly test from November 2, 2024, to December 31, 2025; thus the frozen encoder has no test-period information in its weights.
- Orders are executed at the target weight change each hour without additional market impact beyond the stated fee. execution
Source sentence
Orders are changes from current to target weights, including entries and exits when the eligible list changes, and incur 5 basis points (bps, 0.01%) per unit of absolute traded weight. Our backtest therefore uses the most conservative setting: it charges the base-tier taker fee on every change of the target book at every hourly rebalance, although a policy that trades toward a target book can execute with limit
Show 2 more
- All price and volume data are publicly available and free to use. data
Source sentence
Evaluation design We use cryptocurrency perpetual futures (futures contracts without expiry that can be held long or short) because granular historical trading records are freely and publicly available over long periods.
- Flow matching provides a suitable stochastic policy class for joint allocation of signed weights. model
Source sentence
Flow matching suits portfolio allocation for three reasons. First, the action is a joint distribution over complete books of signed weights, for example, when several correlated assets are candidates for the same short.
Data
2020-01 – 2025-12 · cryptocurrency perpetual futures · crypto · intraday
- Cryptocurrency perpetual futures (hourly bars) market-prices public
Source sentence
Evaluation design We use cryptocurrency perpetual futures (futures contracts without expiry that can be held long or short) because granular historical trading records are freely and publicly available over long periods. Policy training and test samples are strictly separated in time.
Costs
Modeled
A flat 5 bps fee per unit of absolute traded weight is applied to every change of the target book; median half‑spread is 0.24 bps.
Source sentence
Orders are changes from current to target weights, including entries and exits when the eligible list changes, and incur 5 basis points (bps, 0.01%) per unit of absolute traded weight. This fee is the maximum of the base-tier taker fees of major perpetual-futures venues and the fees in prior crypto trading papers, and the median half-spread of the traded contracts is only 0.24 bps (Appendix C.3).
Finds 5
Sharpe 2.19 · annual return 51.4%
- Group‑relative RL refinement raises the annualized net return of the imitation policy from 27.79 % to 51.38 % and its Calmar ratio from 0.955 to 4.043, surpassing the teacher strategy on every metric. performance
Source sentence
On hourly cryptocurrency perpetual futures, RL refinement raises the annualized net return of the imitation policy from $27.79\%$ to $51.38\%$ and its Calmar ratio from $0.955$ to $4.043$, surpassing the teacher strategy on every metric, and AllocFlow reaches a Calmar ratio of $4.90$ on six further months of unseen 2026 data without retraining.
- On six months of unseen 2026 data, AllocFlow achieves a Calmar ratio of 4.90 without retraining. performance
Source sentence
Out-of-sample period Return ↑ MDD ↓ Sharpe ↑ Calmar ↑ Nov 2024–Dec 2025 (Table 1) 51.38 ±2.04 12.81 ±1.51 2.192 ±0.086 4.043 ±0.379 Jan–Jun 2026 (new) 62.53 12.77 2.06 4.90 C.3.
- A parameter‑matched Gaussian policy trained with the same objective attains at most a Calmar of 1.92, less than half of the flow policy’s 4.043. performance
Source sentence
Across exploration scales σ (Table 2b), it reaches a Calmar of at most 1.92, versus 4.043 for the flow policy, and stays below 1 in the other four settings.
- Replacing the frozen Kronos encoder with a frozen iTransformer causes severe performance loss (negative returns and Calmar), showing the importance of good market features. performance
Source sentence
Replacing frozen Kronos with a frozen iTransformer while keeping the flow head loses heavily after both IL and RL on the same ledger (Table 5), and reward refinement does not recover the Kronos-conditioned performance. With the losing Kronos-direct deployment, this shows that good market features become valuable only when a suitable head learns to allocate from them.
- Reward ablation shows that training with a Sharpe‑based reward yields the highest Calmar (4.043) while other reward choices either reduce Calmar or produce negative returns. performance figure from elsewhere in the paper
Source sentence
Cumulative return gives the highest annualized return, but the Sharpe-trained policy has the smallest MDD and highest Calmar while trading more than the return-focused variants, so its downside improvement is not simply the result of trading less; the risk-adjusted-return variant loses money, so nominal risk adjustment does not by itself ensure a useful training signal. Training reward Return MDD Sharpe Calmar TO IL
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 19 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-17 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (66)
- Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading (2026) — link
- Decision-focused Sparse Tangent Portfolio Optimization (2026) — link
- The Label Horizon Paradox: Rethinking Supervision Targets in Financial Forecasting (2026) — link
- Online Portfolio Selection with ML Predictions (2025) — link
- FinCon : A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making (2024) — link
- Learning to Trade via Direct Reinforcement (2001) — link
- A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem (2017) — link
- Online Portfolio Management via Deep Reinforcement Learning with High-Frequency Data (2023) — link
and 58 more
- Soft Imitation Reinforcement Learning with Value Decomposition for Portfolio Management (2024) — link
- AlphaZeroBeta : Deep Reinforcement Learning for Market-Neutral Portfolios (2026) — link
- Smart ``Predict, then Optimize’’ (2022) — link
- Deep Hedging (2018) — link
- Kronos : A Foundation Model for the Language of Financial Markets — → 2508.02739
- iTransformer : Inverted Transformers Are Effective for Time Series Forecasting (2023) — link
- Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning — → 2306.12964
- AlphaSAGE : Structure-Aware Alpha Mining via GFlowNets for Robust Exploration — → 2509.25055
- AlphaAgent : LLM -Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay (2025) — link
- R&D-Agent-Quant : A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization — → 2505.15155
- STABLE : Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates (2026) — link
- Solving Dynamic Portfolio Selection Problems via Score-Based Diffusion Models — → 2507.09916
- Decision-Weighted Flow Matching for Contextual Stochastic Optimization (2026) — link
- Flow Matching for Generative Modeling (2022) — link
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion (2023) — link
- \ensuremath \pi_0 : A Vision-Language-Action Flow Model for General Robot Control (2024) — link
- Diffusion Policy Policy Optimization (2025) — link
- Flow-GRPO : Training Flow Matching Models via Online RL (2025) — link
- ReinFlow : Fine-Tuning Flow Matching Policy with Online Reinforcement Learning (2025) — link
- Robust Performance Hypothesis Testing with the Sharpe Ratio (2008) — link
- The Deflated Sharpe Ratio: Correcting for Selection Bias, Backtest Overfitting, and Non-Normality (2014) — link
- Portfolio Selection (1952) — link
- Empirical Asset Pricing via Machine Learning (2020) — link
- 101 Formulaic Alphas (2016) — link
- Deep Reinforcement Learning for Trading (2020) — link
- Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning (2026) — link
- Realistic Market Impact Modeling for Reinforcement Learning Trading Environments (2026) — link
- Scalable Diffusion Models with Transformers (2022) — link
- Proximal Policy Optimization Algorithms (2017) — link
- DeepSeekMath : Pushing the Limits of Mathematical Reasoning in Open Language Models (2024) — link
- Dynamic Trading with Predictable Returns and Transaction Costs (2013) — link
- OpenClaw-RL : Train Any Agent Simply by Talking (2026) — link
- Deep Direct Reinforcement Learning for Financial Signal Representation and Trading (2017) — link
- One Fits All: Power General Time Series Analysis by Pretrained LM (2023) — link
- Time-LLM : Time Series Forecasting by Reprogramming Large Language Models (2024) — link
- FinRL : A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance (2020) — link
- Deep Reinforcement Learning for Portfolio Selection (2024) — link
- Visual Instruction Tuning (2023)
- CLIPort : What and Where Pathways for Robotic Manipulation (2021)
- GR00T N1 : An Open Foundation Model for Generalist Humanoid Robots (2025) — link
- Deep Learning for Portfolio Optimization (2020)
- MARS : A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management (2026)
- DeepAries : Adaptive Rebalancing Interval Selection for Enhanced Portfolio Selection — → 2510.14985
- Regime-Adaptive Continual Learning for Portfolio Management (2026)
- EarnHFT : Efficient Hierarchical Reinforcement Learning for High Frequency Trading — → 2309.12891
- MacroHFT : Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading — → 2406.14537
- FineFT : Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading (2026)
- ArchetypeTrader : Reinforcement Learning for Selecting and Refining Learnable Strategic Archetypes in Quantitative Trading (2026)
- AlphaGAT : A Two-Stage Learning Approach for Adaptive Portfolio Selection (2025)
- The Recurrent Reinforcement Learning Crypto Agent (2022)
- Directly Fine-Tuning Diffusion Models on Differentiable Rewards (2024)
- Continuous Control with Deep Reinforcement Learning (2016)
- Asynchronous Methods for Deep Reinforcement Learning (2016)
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor (2018)
- Addressing Function Approximation Error in Actor-Critic Methods (2018)
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (2017)
- The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games (2022)
- Human-Level Control through Deep Reinforcement Learning (2015)
8 of 66 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.