Newest papers

Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research

Houde Qian, Zheng Jiang, WenYi Li, Chenxi Xu, Xinjie Lin, Yuzhao Peng, Ruoyu Han, Youjie Zheng, Kaisen Yang, Qinhuai Na, You Fu, Calvin Xiao · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30113 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Penelitian kuantitatif adalah loop iteratif: seorang peneliti mengusulkan hipotesis pasar, mengimplementasikannya sebagai sinyal yang dapat dieksekusi, mengujinya pada data historis, dan memutuskan apa yang harus disimpan. Referensi yang ada mencetak rumus, kode, atau keputusan perdagangan individu, meninggalkan terbuka apakah model bahasa besar (LLM) dapat menyelesaikan loop ini dan menghasilkan strategi yang bekerja melampaui periode penelitian. Kami memperkenalkan Quant-Arena, sebuah benchmark dan papan panduan publik untuk penelitian kuantitatif end-to-end pada data pasar A-share nyata. Sebuah model membangun fitur dan kode penilaian saham, menerima umpan balik hanya pada 2022-2023 dan membekukan satu strategi untuk penilaian pada tahun 2024. Sebuah penilaian rekening tunai menerapkan pembatasan perdagangan dan biaya, termasuk perkiraan pasar yang dipengaruhi dari buku pes

Machine translation (Meta M2M100); the English original follows.

Abstract

Quantitative research is an iterative loop: a researcher proposes a market hypothesis, implements it as an executable signal, tests it on historical data, and decides what to keep. Existing benchmarks score formulas, code, or individual trading decisions, leaving open whether large language models (LLMs) can complete this loop and produce strategies that work beyond the research period. We introduce Quant-Arena, a benchmark and public leaderboard for end-to-end quantitative research on real A-share market data. A model constructs features and stock-scoring code, receives feedback only on 2022--2023, and freezes one strategy for assessment on the sealed year 2024. A cash-account evaluator applies trading constraints and costs, including market impact estimated from a simulated order book. Scores are dominated by realized excess return and complemented by signal quality and the diversity of features used by the strategy. We evaluate nine frontier models, among which GPT-6 Astra scores highest; yet no model beats the equal-weight market in 2024. Quant-Arena is open to submissions from any model or agent harness.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Benchmarking, Executable, Benchmark (surveying), Computer science, Order (exchange), Algorithmic trading

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange