Top AI-Driven Quantitative Finance Papers from AAAI 2026
This article curates and summarizes recent AI research papers presented at AAAI 2026 that advance quantitative finance, covering controllable market generation, LLM‑powered alpha factor mining, risk‑aware multi‑agent portfolio management, foundation models for market data, and reinforcement‑learning trading policies.
Controllable Financial Market Generation with Diffusion Guided Meta Agent (DigMA)
Paper link: https://arxiv.org/pdf/2408.12991<br/> Code link: https://github.com/microsoft/TimeCraft<br/> Authors: Yu‑Hao Huang, Chang Xu, Yang Liu, Weiqing Liu, Wu‑Jun Li, Jiang Bian
Abstract: Generative modeling has excelled in language and vision, yet its application to financial markets remains limited. Existing order‑flow models suffer from low fidelity and lack controllability. This work defines the challenges of controllable financial market generation and proposes the Diffusion Guided Meta Agent (DigMA) model. DigMA uses a conditional diffusion model to capture market‑state dynamics represented by intermediate price‑return and order‑arrival rate distributions, and introduces a meta‑agent with financial‑economic priors to generate orders from these distributions. Extensive experiments demonstrate superior controllability and fidelity, validating DigMA as an effective and efficient environment for downstream high‑frequency trading tasks.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.