arXiv cs.AI· Owen Queen, Ioana Ciuca, Emma Dann, Jean Somalwar, Carine You, Steven Dillmann, Viraj Manwadkar, Evan Gorrell, Harrison G Zhang, Jonathan K Pritchard, Risa H Wechsler, James Zou·· 4 小时前AI 评分57
DiscoveryAgent:以科学家为中心的智能体式 AI 框架
DiscoveryAgent: A Framework for Scientist-centric Agentic AI
AI 导读
研究团队提出 DiscoveryAgent,一个领域无关、以科学家为中心的科研智能体系统,科学家可在研究轮次之间选择、细化或替换假设,审计智能体则查询带检查点的记录以追溯结论、复现分析。
正文 · 原文
Authors:Owen Queen, Ioana Ciuca, Emma Dann, Jean Somalwar, Carine You, Steven Dillmann, Viraj Manwadkar, Evan Gorrell, Harrison G Zhang, Jonathan K Pritchard, Risa H Wechsler, James Zou
Abstract:AI agents can assist scientific research, but balancing autonomous investigation with scientists' ability to inspect and redirect ongoing work remains a central design challenge. We present DiscoveryAgent, a domain-agnostic, scientist-centric system that combines autonomous investigation with scientist-directed hypothesis steering. Scientists select, refine, or replace hypotheses between research rounds, while audit agents interrogate checkpointed records to trace claims, reproduce analyses, and inform subsequent decisions. Across two predictive modeling tasks, DiscoveryAgent produced the best variable-star classifier among evaluated baselines and, with scientist steering, a protein variant-effect predictor surpassed by only one of 106 ProteinGym baselines. We develop a rigorous checkpointing system that enables highly capable audit agents, a scalable form of oversight for agentic research. Audit agents autonomously identify errors at higher rates than previous AI scientist agents, and scientists collaborating with audit agents identify 14x more valid errors versus scientists performing manual review. In three case studies led by domain experts across physical science, social science, and life science, we developed a multimodal photometric-redshift estimator that resolves complementary failures of images and photometry, achieving 0.971 AUROC for low-redshift classification; documented an 83% rise in Florida homeowners-insurance premiums from 2013 to 2023, with a growing, regressive burden; and identified CD4+ T-cell relay genes, which both receive and exert broad transcriptional regulation, enriched for autoimmune disease associations. Together, these results show how autonomous research can expand scientists' empirical reach while centering their authority over research direction and their ability to understand and challenge the evidence.
| Comments: | Supplementary information is available as an ancillary file (this http URL) |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.21950 [cs.AI] |
| (or arXiv:2611.21950v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21950 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Owen Queen [view email]
[v1]
Mon, 16 Nov 2026 22:17:37 UTC (31,640 KB)
来源:arXiv cs.AI · arxiv.org