综合赛事提交 Docker 智能体 + 沙箱评测奖金剩 9 天

Agenthon 2026

Agenthon 2026 由 Society of Quantitative Analysts & CEWIT, Stony Brook University 主办。报名截止 9月28日（剩 9 天）。举办地区：全球、线上。参赛对象：开发者、研究者、其他。奖励：TBD（未公布）

主办方：Society of Quantitative Analysts & CEWIT, Stony Brook University· 来源智能体赛事网络发现 · 最近核验 8/23 01:11

前往官网报名

赛事介绍

Verifiable AI for quantitative finance。提交 Docker 智能体，四赛道：T1 量化金融编码、T2 时序推理预测、T3 市场加速仿真、T4 证据驱动预测。每提交需通过 g0-g3 完整性/模式/资源/语义闸门。注册 8/17-9/28，开发 8/28-9/28，最终 9/29-10/12，验证 10/13-25，NeurIPS Atlanta 工作坊 12/9-13。

关键时间

报名8月17日 - 9月28日

赛事8月28日 - 12月13日

参赛条件与赛事信息

参赛对象: 开发者 · 研究者 · 其他原始标注：开发者 · 研究者 · 金融从业者
举办地区: 全球 · 线上
报名截止: 9月28日（剩 9 天）
奖励: TBD（未公布）
赛事形式: 提交 Docker 智能体 + 沙箱评测
落地要求: 无（可远程）
报名入口: https://www.agenthon.net/

参赛资格

官方标注里没有排他的身份要求，符合赛事对象即可报名。

接受身份: 未标注（视为不限）
附加要求: 有人数限制

报名要求

1-3 人队伍
Docker 容器提交
通过 g0-g3 闸门
来源证据：https://www.agentdeadlines.com/

同类赛事

数据来源

本页信息来自公开来源（智能体赛事网络发现），最近核验于 8/23 01:11。赛事规则以主办方官方页面为准。

官方页面原文摘录

展开原文（5743 字）

NEURIPS 2026 COMPETITION TRACK Agenthon 2026 Verifiable AI for quantitative finance. A four-track competition testing whether AI agents can produce finance outputs that survive automated, leakage-controlled, cheat-resistant evaluation. Explore tracks How scoring works SUBMISSION Docker agent ADMISSIBILITY g0-g3 gates RANKING Track metrics KEY DATES Registration opens Monday. Registration runs from 17 August to 28 September, so you can enter at any point while Development is under way. 17 AUG – 28 SEP Registration Sign up and form your team. Opens Monday, 17 August. 28 AUG – 28 SEP Development Public practice repositories, iteration, and the validation leaderboard. 29 SEP – 12 OCT Final One final submission per entered track is evaluated on sealed held-out units. 13 – 25 OCT Verification Top submissions are rerun and reviewed for reproducibility. 9 – 13 DEC NeurIPS, Atlanta Workshop and final presentations by the winners, in Atlanta, Georgia. The competition closes with a workshop and final presentations from the winning teams at NeurIPS in Atlanta, Georgia. The exact session date is set by NeurIPS and will be announced. All dates are given in the official rules, which govern if anything here is out of step. TEAMS Enter as a team of one to three. You can compete alone or with up to two teammates. You join one team and stay on it, and that one team can enter as many of the four tracks as it wants. Registration is per team, and only registered teams can get the starter package, submit solutions, or appear on the leaderboard. Have a question about entering? Start with the FAQ. CORE QUESTION Can AI agents produce finance answers that can be checked by machine? Agenthon extends the Alphathon program into its first NeurIPS edition. The competition keeps the four-track structure and hard finance setting, while adding sealed held-out data, automated leakage controls, reproducible reruns, and public leaderboards. Every official submission runs offline in a sandboxed Docker container. It must pass integrity, schema, cutoff/resource, and domain-semantics gates before any leaderboard metric is computed. FOUR TRACKS Same competition spine, four finance problems. T1 CODING Quant-finance coding agents Build a Docker agent that solves quantitative finance coding tasks under pytest and financial-invariant checks. Verb solve Metric pass@1 / pass@3 Gate pytest + invariants T2 FORECASTING Reasoning-augmented time series Forecast future panels using time-series data plus a time-stamped text corpus, then prove information uplift over text-blind baselines. Verb forecast Metric CRPS composite Gate as-of cutoff + calibration T3 SIMULATION Accelerated market simulation Submit an ABIDES-compatible simulator that is faster while preserving matching-engine semantics and market stylized facts. Verb simulate Metric events/sec Gate semantic regression T4 EXPLAINABILITY Evidence-grounded prediction Predict labels, values, or rankings over tabular entities with citations from a frozen evidence corpus and confidence intervals. Verb analyze Metric quality + coverage Gate faithfulness + embargo PROTOCOL Submit, check, score. The visible rule is simple. A submission is ranked only after it passes the same admissibility sequence used by every track. 01 Submit A Docker image implements one stable CLI verb for its track. 02 Check g0-g3 verify integrity, schema, cutoff/resource rules, and domain semantics. 03 Score Only admissible runs receive a track metric and bootstrap confidence interval. PUBLIC/PRIVATE FIREWALL Transparent grading, sealed answers. Each track has a public practice repo and a private sealed exam repo. Public repos include practice tasks, baselines, smoke scorers, and participant docs. Private repos hold held-out tasks, oracle keys, final scoring logic, and audit material. PUBLIC PRACTICE PRIVATE EXAM Public-dev and validation units Private-test held-out units Runnable baselines and smoke scorer Oracle solutions and final scorer Manifest and canary safety checks Canary registry and audit logs LEADERBOARD Competition scores will appear here. Each team row will show its total score first. Expanding a row reveals the per-track score breakdown used to compute or explain that total. RANK TEAM TOTAL BREAKDOWN -- Team placeholder 01 -- View tracks -- Team placeholder 02 -- View tracks -- Team placeholder 03 -- View tracks 2026 PHASES Development, final, verification. UPCOMING Development opens in 3 days Public repos open, teams practice, and the validation leaderboard goes live. Starts Aug 28. 0% COMPLETE UPCOMING Aug 28 - Sep 28 Development Public repos open. Teams practice, iterate, and use the live validation leaderboard. UPCOMING Sep 29 - Oct 12 Final One submission per entered track is evaluated on sealed private-test units with a hidden leaderboard. UPCOMING Oct 13 - Oct 25 Verification Organizers rerun top submissions with fresh seeds and review reproducibility. SCIENTIFIC OUTPUTS Agenthon is designed to explain failures, not just rank winners. Cross-track failure map Gate failures are labeled and aggregated to show where finance agents break down. Information uplift T2 isolates whether text and reasoning beat strong text-blind forecasting baselines. Speed-realism frontier T3 measures throughput only after semantic fidelity and stylized facts survive checks. Faithfulness under embargo T4 requires evidence-backed predictions that do not cite future or unsupported facts.