Position: AI-Assisted Peer Review Should Be Designed for Interdisciplinary Evaluation

AI-assisted peer review is becoming part of conference infrastructure, while major machine-learning venues increasingly solicit interdisciplinary work whose evaluation may depend on knowledge outside the assigned reviewer’s field. We argue that interdisciplinary evaluation should become a first-class, benchmarkable objective of AI-assisted peer review. We introduce material cross-disciplinary dependencies: claims for which external disciplinary knowledge could plausibly change a reviewer’s judgment of correctness, novelty, or significance. We propose a claim-level interdisciplinary context layer that identifies such dependencies, searches across disciplinary vocabularies, retrieves source-linked evidence, and flags unresolved expertise gaps for human review. We further argue that cross-field prior art should inform, rather than determine, contribution judgments: reviewers should distinguish redundant rediscovery, substantive adaptation, and consequential transfer. The aim is not to favor interdisciplinary work or add a second full review, but to use AI assistance selectively where local expertise may be insufficient.