arXiv cs.AI· Tian Cai, Andrew Kleist, Jaimin Patel, Duccio Malinverni, Alexander K. Taylor, Malvika Sharan, Renato Umeton, M. Madan Babu·· 3 小时前AI 评分34
AI for Biologists：智能体时代基础模型的知识边界综述
AI for Biologists: The Knowledge Boundaries of Foundation Models in the Age of Agentic Systems
AI 导读
一篇将发表于 Annual Review of Biomedical Data Science 的综述把生物基础模型和基于大语言模型的智能体系统的可靠性问题归纳为"知识边界"，即模型输出可靠时涵盖的输入、任务和条件范围。作者提出数据、架构、训练方案、评估方案和后分析五项设计要素共同决定这一边界，并给出标准化的模型局限描述，帮助研究者及其智能体可靠使用这些工具。
正文 · 原文
Abstract:Artificial intelligence (AI) is changing how biological research is done. Biological foundation models trained on millions of nucleotides, protein, and single-cell measurements predict protein structures, mutation effects, and cellular responses to genetic perturbations. Agentic systems, AI assistants built on large language models, can run multistep analyses from plain-language requests and increasingly call foundation models as tools. Yet it is often unclear when these models' outputs can be trusted. We frame this as a model's knowledge boundary: the range of inputs, tasks, and conditions over which its outputs are reliable. This review explains how foundation models are built and proposes that five design elements (data, architecture, training scheme, evaluation scheme, and post-analysis) define this boundary. We examine evidence on where current models succeed or fail and present standardized descriptions of model limits so that researchers, and the agents acting for them, can use these tools reliably.
| Comments: | To be published on Annual Review Biomedical Data Science |
| Subjects: | Biomolecules (q-bio.BM); Artificial Intelligence (cs.AI) |
| MSC classes: | 92C40, 68T07, 92-08 |
| ACM classes: | I.2.6; J.3 |
| Cite as: | arXiv:2611.17015 [q-bio.BM] |
| (or arXiv:2611.17015v1 [q-bio.BM] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17015 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tian Cai [view email]
[v1]
Thu, 12 Nov 2026 16:08:33 UTC (1,907 KB)
来源：arXiv cs.AI · arxiv.org