High-grade serous ovarian cancer (HGSOC) remains a major clinical challenge. In particular among those patients with homologous recombination (HR)-proficient tumors (>50%), most eventually succumb to their disease due to high recurrence rates, acquired resistance, and cumulative toxicity. This report summarizes work from the 12th IMO Workshop in which we explored an alternative “extinction therapy” strategy for frontline treatment of HGSOC. Inspired by ecological principles, this multi-strike approach aims to eradicate tumors not through a singular “magic bullet” but through a series of therapies after standard frontline treatment when the tumor is still, and perhaps most, vulnerable. We present a framework leveraging mathematical modeling (MM) to develop personalized multi-strike protocols for HGSOC. Key contributions include: 1) An “IMOme” score using liquid biopsy data to assess patient-specific hematopoietic toxicity risk, guiding the timing and selection of subsequent therapies, 2) MM strategies to design effective lowdose combinations of targeted agents to achieve synthetic lethality while managing toxicity, and 3) A MM framework to analyze the interplay between chemotherapy, gut microbiome toxicity, and immunotherapy, demonstrating how mitigating microbiome damage could enhance immune response. Overall, the computational approaches presented herein aim to support the design of personalized, multi-strike regimens in the frontline setting that proactively target tumor extinction while managing toxicity, ultimately seeking to deliver cures for patients with HGSOC.

Artificial intelligence is revolutionizing oncology by transforming how malignancies are diagnosed, cancer biology is understood, and therapeutics are discovered. A cornerstone of this progress has been the availability of extensive, carefully curated datasets. Similarly, advances in AI-guided therapeutic strategies via Reinforcement Learning (RL) hinge upon carefully designed computational training environments that are both efficient and sufficiently realistic to capture key dynamics of cancer growth and therapy response. However, designing suitable models remains challenging for solid tumors, where emergent physical phenomena significantly influence therapeutic outcomes. Here, we introduce Reinforcement Failing, an AI-guided scientific discovery framework designed to reveal emergent physical mechanisms in tumor therapy. Applying this approach to adaptive therapy in solid tumors, we identify the pivotal roles of position-dependent proliferation and mechanically driven collective motion of resistant cells. Our findings highlight how integrating tumor physics into therapeutic strategies can optimize outcomes while mitigating hidden pitfalls during translation. Together, these results demonstrate that Reinforcement Failing is a powerful artificial scientific discovery engine for deciphering high-complexity processes in personalized cancer treatment and beyond.