跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-20AI 評分59

Agent4Sci:前沿智能體能否在真實環境中推進科學機器學習?

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

AI 導讀

Agent4Sci 評估前沿編碼智能體在科學機器學習基準上的改進能力,發現它們在 20 個基準、11 個領域均提升已發表的最佳模型。Claude Opus 平均相對提升 10.4%,但增益幾乎全來自機器學習工程技巧,而非研究級洞見。加入研究構思、實驗管理和定時檢查清單等輕量插件技能後,Claude Opus 提升至 20.1%,Codex 則由 4.4% 升至 8.1%。

正文

Published on Oct 20

Authors:

,

,

Abstract

Agent4Sci evaluates frontier coding agents on scientific ML benchmarks, finding they improve results mainly through engineering tricks rather than domain insight, with targeted skills significantly boosting performance.

Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain insight beyond routine ML engineering. We introduce Agent4Sci, a long-horizon testbed for measuring how far today's agents can improve the published best models on scientific ML benchmarks, spanning 20 benchmarks across 11 domains. Rather than ranking agents on a leaderboard, Agent4Sci asks what kinds of progress agents can make on these tasks under in-the-wild conditions, and where they fall short. Empirically, today's frontier agents advance the published best on every benchmark, with Claude Opus reaching 10.4% mean relative improvement and no run flagged for academic misconduct. These gains, however, come almost entirely from a bag of ML-engineering tricks rather than research-level insight. Trajectory analysis surfaces three recurring limitations in this setting: novelty miscalibration, resource under-utilization, and rapid collapse into local engineering sweeps. Lightweight plug-in skills for research ideation, experiment management, and scheduled checklists raise Claude Opus from 10.4% to 20.1% and Codex from 4.4% to 8.1%, while yielding more diverse, domain-relevant interventions. Agent4Sci gives the community a way to track and push frontier agents from ML engineering toward domain insight on real-world ML-for-science problems. Code and data are available on GitHub (https://github.com/maszhongming/agent4sci) and Hugging Face (https://huggingface.co/datasets/MingZhong/agent4sci).

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.28763

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.28763 in a model README.md to link it from this page.

Datasets citing this paper 1

MingZhong/agent4sci

Updated 27 minutes ago

•

53

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.28763 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co