PyTorchKR Papers

최신 논문

총 2편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2604.25345v2cs.AI

Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows

Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical tasks. In the One-Shot setting, access to domain-specific context yields an approximately ~6x performance improvement (0.85 vs. ~0 without context), with the primary failure mode being silent incorrect computation - syntactically valid code that produces plausible but inaccurate results. In the Deep Research setting, the system frequently exhibits silent failures across stress tests, producing physically inconsistent posteriors without self-diagnosis. Overall, performance is strong on well-specified tasks but degrades on problems designed to probe reasoning limits, often without visible error signals. These findings highlight that the most concerning failure mode in agentic scientific workflows is not overt failure, but confident generation of incorrect results. We release our evaluation framework to facilitate systematic reliability analysis of scientific AI agents.

arXiv:2606.18425v1cs.SE

명세에서 실행까지: AI 지원 과학적 워크플로우 관리

From Specification to Execution: AI Assisted Scientific Workflow Management

과학적 워크플로우 관리를 위해 워크플로우 의도·설계·구현을 분리하는 명세 기반 생성, 다층 실패를 진단·복구하는 LLM 디버깅 에이전트, Pegasus WMS와 모델 컨텍스트 프로토콜(MCP) 통합을 결합한 AI 지원 접근 방식을 제안한다. 의료 영상 연합 학습(federated learning) 평가에서 수천 개 작업 규모의 워크플로우를 생성·실행하며 디버깅 부담을 줄였고, 비전문가도 전문가 수준의 설계 패턴으로 워크플로우를 구성할 수 있음을 보였다.