PyTorchKR Papers

최신 논문

총 2편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2606.31085v1cs.AI

DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction

Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose relevance changes across interaction mechanisms. We propose DDIAgents, a mechanism-conditioned multi-agent framework that performs DDI prediction through dynamic knowledge orchestration. Given a drug pair, a planner agent instantiates specialized expert agents, routes mechanism-relevant knowledge sources to each agent, and aggregates their analyses through a conclusion agent. By adapting context flow to the inferred interaction mechanism, DDIAgents reduces irrelevant information, supports complementary expert reasoning, and produces interpretable agent-level rationales. Extensive experiments on realistic DDI prediction benchmarks show that DDIAgents consistently outperforms existing feature-based, graph-based, LLM-based, and agent-based baselines. Beyond prediction performance, DDIAgents demonstrates how multi-agent systems can organize heterogeneous scientific knowledge for adaptive and interpretable AI4Science reasoning.

arXiv:2606.18936v1cs.AI

SciRisk-Bench: AI4Science 안전성을 위한 위험 차원 인식 벤치마크

SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety

AI4Science 워크플로우에서 LLM의 안전성을 명시적 위험 차원과 과학 학문 분야 관점에서 평가하기 위해 7개 학문 분야, 31개 세부 전공, 10개 위험 차원을 포괄하는 SciRisk-Bench 벤치마크를 제안한다. 주류 LLM과 과학 지향 LLM을 위험 차원·학문 분야·세부 전공별로 평가한 결과, 과학 특화 모델이 더 높은 공격 성공률(ASR)을 보이는 등 모델이 여전히 안전하지 않은 지점을 정밀히 진단할 수 있다.