오픈소스 종양학 에이전트 OncoAgent, 56배 학습 속도 향상 달성
개인정보 보호형 종양학 지원 에이전트인 OncoAgent는 AMD MI300X 하드웨어에서 50분 만에 학습되어 API 방식 대비 56배 속도 향상을 달성했습니다.
the oncoagent research group published a technical preprint for oncoagent, a multi-agent framework designed for privacy-preserving oncology support. the system routes queries to 9b or 27b models fine-tuned via qdora on amd instinct mi300x hardware, processing 266,854 real and synthetic cases. hardware-specific optimizations enabled full dataset training in approximately 50 minutes, marking a 56× improvement over api-based generation. the architecture utilizes a four-stage corrective rag pipeline with 100% grading success and a reflexion safety validator to ensure data sovereignty.