Can AI agents conduct open-ended AI research? Early evidence from two case studies
Authors: Peter Kirgis, Sayash Kapoor, Andrew Schwartz, Stephan Rabanser, David Africa, Konstantinos Voudouris, Viet Nguyen, Toby Pilditch, Magda Dubois, Harry Coppock, Cozmin Ududec, Nitya Nadgir, Matilda Orona, Tilman Bayer, Derrick Chan-Sew, Yue Ling, Abhishek Shetty, Helen Toner, Gillian Hadfield, Seth Lazar, Steve Newman, Shoshannah Tekofsky, Rishi Bommasani, Arvind Narayanan
Published: 2026-07-29
Categories: cs.AI, cs.CY, cs.LG
arXiv: 2607.27191
Abstract
Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is thin. Current evaluations either test agents on narrow, verifiable tasks, which excludes open-ended research, or submit AI-generated papers to blind peer review, which is overstretched, stochastic, and suffers from poor review quality. We introduce a third way to measure progress towards AI R&D automation. An agent takes on the central, open-ended research question of a high-quality unpublished paper, and the paper's original authors grade its output. We call these shadow evaluations. We ran shadow evaluations on two unpublished NeurIPS 2026 submissions, giving frontier agents six days and thousands of dollars of compute. The agents completed all of the engineering without human help, yet could not make substantial progress towards answering the research questions. As a result, both papers were unambiguously rejected by the authors. We identify five recurring failure modes: poor judgment about the bar for publishable research, uncreative responses to shortcomings in the research design, ineffective backtracking from dead ends, poor resource awareness, and instruction drift. A robustness check with a second model and scaffold reproduced these failures. We release the expert reviews, survey responses, agent repositories, and logs. Our results provide early evidence that today's agents can do the engineering of AI research, but struggle with critical parts of the research lifecycle.
中文概述
这篇论文提出了一种名为“影子评估（shadow evaluation）”的方法来测量 AI 代理是否能进行开放式 AI 研究。前沿代理在两篇未发表的 NeurIPS 2026 投稿上获得了六天计算资源，能独立完成所有工程实现，但无法实质性地回答研究问题。作者识别了五种常见失败模式：对可发表研究门槛的判断不足、对研究设计缺陷的创造性回应不足、无法从死胡同环境中回溯、资源意识不足、以及指令漂移。这为“当前代理能做工程但难以做研究”提供了早期证据。
关键发现
- 提出“影子评估”方法：代理接手未发表论文的核心开放问题，由原作者评分
- 前沿代理独立完成全部工程实现，但无法实质推进研究问题
- 五大失败模式：研究门槛判断、创造性不足、回溯失效、资源意识、指令漂移
- 第二个模型 + scaffold 复现了同样的失败
信息来源
- 论文链接: https://arxiv.org/abs/2607.27191
- PDF: https://arxiv.org/pdf/2607.27191v1
- 主要类别: cs.AI, cs.CY, cs.LG