arXiv：cs.AI· Nam H. Le, Douglas Blackiston, Michael Levin, Josh Bongard·· 4 小时前AI 评分44
用语言控制生物学：细胞、类器官与生物机器人的提示词条件干预离线学习
Toward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots
AI 导读
研究者提出一种完全离线的语言到干预映射学习方法，以视觉语言模型自身的判断作为唯一训练奖励，为无神经系统的合成多细胞构造 xenobot 构建自然语言接口，将指令映射到档案中已记录、能产生所述行为的干预。该映射可泛化到全新指令，在未参与训练的档案数据上取得 80.0% 的留出准确率，高于 66.7% 的随机基线，并与直接用真实标签训练的模型相当。
正文
Abstract:Artificial intelligence increasingly serves as a natural-language interface to complex technical systems, letting people accomplish sophisticated tasks by describing what they want rather than specifying how to do it. Extending this interface to living systems is harder: unlike code or images, a biological intervention has no closed-form linguistic meaning, and the paired language-intervention-outcome data needed to learn such a mapping is expensive to collect, since each example requires its own wet-lab experiment. One way around this is to treat an existing archive of interventions and their already-observed outcomes as a fixed, offline dataset, and use a vision-language model to judge, without any new experiments, whether an archived outcome matches a natural-language description. But whether that judgment is reliable enough to train a language-to-intervention mapping on -- without new experiments and without human validation -- has remained unclear. Here we show that a natural-language interface for a living organism -- a xenobot, a synthetic multicellular construct with no nervous system -- can be learned entirely offline this way, using a vision-language model's own judgment as the sole training reward: an instruction is mapped to the intervention already on record as producing the described behavior. This mapping generalizes to entirely new instructions, evaluated against archive data withheld from training (80.0% held-out accuracy vs a $66.7% chance baseline, matching a network trained directly on ground-truth labels).
| Subjects: | Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Neural and Evolutionary Computing (cs.NE); Robotics (cs.RO) |
| Cite as: | arXiv:2610.02247 [q-bio.QM] |
| (or arXiv:2610.02247v1 [q-bio.QM] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02247 arXiv-issued DOI via DataCite |
Submission history
From: Nam H. Le [view email]
[v1]
Wed, 30 Sep 2026 16:49:01 UTC (10,000 KB)
来源：arXiv：cs.AI · arxiv.org