Metraipolis › archive › dc_75d4fece5004
CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling — arXiv:2609.19970
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19970
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:08:50.552Z
- SHA-256 of the archived text
1ccc1c27c8a8e85d402781cd9eca3b6afa74d8cad8e8301be734ed1fa11ad9de- Stable URL of this page
https://metraipolis.com/documento/dc_75d4fece5004
How to cite
CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling — arXiv:2609.19970 — arXiv (en), https://arxiv.org/abs/2609.19970 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75d4fece5004 (Metraipolis archive dc_75d4fece5004, sha256 1ccc1c27c8a8e85d402781cd9eca3b6afa74d8cad8e8301be734ed1fa11ad9de)
BibTeX
@misc{dc75d4fece5004,
title = {CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling — arXiv:2609.19970},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19970},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75d4fece5004; sha256 1ccc1c27c8a8e85d402781cd9eca3b6afa74d8cad8e8301be734ed1fa11ad9de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19970. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predicting cellular responses to perturbations supports the study of gene function, disease mechanisms, and therapeutic strategies. Despite advances in single-cell perturbation modeling, existing models typically optimize surrogate losses that do not directly reflect the biological criteria used for evaluation, so better data fitting need not yield better biological predictions. To address this mismatch, we introduce \textbf{CellRFT}, a reinforcement fine-tuning framework that uses biological evaluation as direct training feedback. CellRFT uses policy-gradient optimization to learn from non-differentiable evaluations of generated cell populations and integrates multiple biological rewards through hierarchical reward aggregation. Comprehensive experiments demonstrate CellRFT's applicability across different pretrained models and effectiveness in improving perturbation prediction, reveal that optimizing one biological criterion can help or hinder others, and show that complementary rewards can improve criteria beyond those directly optimized, offering a way to probe how biological metrics shape model behavior, with the potential to inform evaluation design. Code will be made available.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19970 — 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 2026-10-10T03:48:18.310Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).