VIDHAAN APPAJI; LOKESH UPPUTRI; SENTHIL ARASU T; DAKSHA S. Small Models, Precisely Tuned: A Two-Tier Small-Language-Model Architecture for Autonomous Penetration Testing Soft-Prompt-Tuned Strategic Reasoning Paired with a LoRA-Fine-Tuned Tool-Calling Executor, Evaluated Against VAmPI and OWASP Juice Shop. International Journal of Innovations in Science Engineering And Management, India, v. 5, n. 4, p. 229–243, 2026. DOI: 10.69968/ijisem.2026v5i4229-243. Disponível em: https://www.ijisem.com/journal/index.php/ijisem/article/view/757. Acesso em: 28 oct. 2026.