Metraipolis › archive › dc_d5cbe134a01d
PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data — arXiv:2608.16419
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16419
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:07:14.896Z
- SHA-256 of the archived text
69f46153fbcbf4f855a4069f3d59705ff07c67fe8a98564f23a1542767aa3dfd- Stable URL of this page
https://metraipolis.com/documento/dc_d5cbe134a01d
How to cite
PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data — arXiv:2608.16419 — arXiv (en), https://arxiv.org/abs/2608.16419 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5cbe134a01d (Metraipolis archive dc_d5cbe134a01d, sha256 69f46153fbcbf4f855a4069f3d59705ff07c67fe8a98564f23a1542767aa3dfd)
BibTeX
@misc{dcd5cbe134a01d,
title = {PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data — arXiv:2608.16419},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16419},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5cbe134a01d; sha256 69f46153fbcbf4f855a4069f3d59705ff07c67fe8a98564f23a1542767aa3dfd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16419. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that cellular perturbation atlases can instead become reinforcement-learning environments, where measured gene responses provide computable rewards for biological reasoning. We introduce PertMind, which combines trusted-trajectory supervised initialization with gene-, pathway-, and format-level reinforcement signals. Although trained only on forward perturbation-response prediction, PertMind improves response inference in unseen cellular contexts while retaining general language capabilities. It also transfers, without task-specific post-training, to reverse perturbation identification, double-perturbation reasoning, phenotypic-screen prioritization, and biological-process interpretation. PertMind further generates biological profiles that support competitive gene, cell, and donor representations across multiscale downstream tasks. These results support the hypothesis that reinforcement on experimental endpoints can concentrate reusable biological strategies already accessible to pretrained models. More broadly, perturbation-derived reinforcement learning offers a scalable route for transforming expanding experimental atlases into training environments for general-purpose biological reasoning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2608.16419 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:14.117Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).