Newest papers

Structure Before Intelligence: Gating What Agentic Scientific Workflows Release

Ashish Acharya, Aman Al Amin, Hong Qin · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.19507 · cited by 0 works (OpenAlex) · open-access PDF

Korean

이 기관적 인 과학적 이익 작업 흐름이 완료되거나 여전히 잘못된 결과를 발표할 수 있는지 여부: 침묵적 인 수치 오류, 안정적인 입력 또는 공유 상승 단계의 결함은 여러 출력 에이전트를 오염시킬 수 있으며 형제 부문이 올바르게 유지됩니다. 우리는 그러한 결과에 대한 신뢰를 릴리스 결정으로 취급합니다. 작업 흐름의 지시된 아시클릭 그래프 (DAG) 주위의 릴리스는 어떤 출력을 사용할 수 있는지 결정합니다 : 그것은 의무적 인 검사를 시행하지만, 영향을받은 부문에 실패를 포함하고, 추적 된 기본 버전으로부터 복구, 검증자를 추가하고, 각각의 위험 모델이 무효의 가능성을 낮은 것으로 추정하는 경우에만 결과

Machine translation (Meta M2M100); the English original follows.

Abstract

An agentic scientific workflow can run to completion and still release wrong results: a silent numerical error, a stale input, or a defect in a shared upstream step can contaminate several outputs while a sibling branch stays correct. We treat trust in such results as a release decision. A harness around the workflow's directed acyclic graph (DAG) decides which outputs may be used: it enforces mandatory checks, contains failures to the affected branch, recomputes from tracked versions, adds validators, and releases a result only if a risk model estimates its probability of being invalid as low. Language-model agents work inside the harness, choosing corrective actions and reviewing releases, but cannot override it. On 60 held-out paired instances of two workflows with injected faults, we switched components on and off. Each supplied a different property. Containment and recovery raised the number of correct results. Validation supplied safety: fixed rules without validation released 37 invalid results, while validating every candidate released none. Risk estimation supplied efficiency, matching that safety with 31% fewer validators at somewhat lower yield, although better targeting than random validation was not shown. Lineage evidence helped on one workflow. The language model added no measurable benefit: whether invalid results escaped depended on the harness, not the model. This proof of concept points to a practical path: placing agents inside explicit release-control structure can keep released scientific results trustworthy, and it gives more capable agents a measurable baseline to improve on.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Workflow, Directed acyclic graph, Computer science, Matching (statistics), Task (project management), Work (physics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange