Thanks to ACM-W scholarship, I was able to present my first authored, full paper “Scheming Ability in LLM-to-LLM Strategic Interactions” as a poster at LaMAS workshop of AAAI-26. This presentation allowed me to share my insights on investigating scheming capability and propensity, which indicate unsafe behaviors that go out of human detection, in multi-agent systems. My poster received substantial interest from students and researchers attending the conference, signalling a crucial attention needed to safeguard humanity future with advanced AI systems.