TY - RPRT TI - rbio1-training scientific reasoning LLMs with biological world models as soft verifiers AU - Istrate, A.-M. AU - Milletari, F. AU - Castrotorres, F. AU - Tomczak, J. M. AU - Torkar, M. AU - Li, D. AU - Karaletsos, T. PY - 2025 DO - 10.1101/2025.08.18.670981 UR - https://www.biorxiv.org/content/10.1101/2025.08.18.670981v1 ID - 10.1101/2025.08.18.670981 ER -