M-ArtAgent: Evidence-Based Multimodal Agent for Implicit Art Influence Discovery
Hanyi Liu, Zhonghao Jiu, Minghao Wang, Yuhang Xie, Heran Yang

TL;DR
M-ArtAgent is a multimodal, evidence-based system that improves implicit art influence discovery by using probabilistic adjudication, formal analysis, and adversarial falsification, achieving high accuracy on a benchmark dataset.
Contribution
It introduces a novel probabilistic adjudication framework with formal operators and falsification techniques for more reliable influence detection in art history.
Findings
Achieves 83.7% F1 score on WIB-100 benchmark.
Demonstrates robustness when influence phrases are masked.
Couples multimodal perception with domain-specific falsification.
Abstract
Implicit artistic influence, although visually plausible, is often undocumented and thus poses a historically constrained attribution problem: resemblance is necessary but not sufficient evidence. Most prior systems reduce influence discovery to embedding similarity or label-driven graph completion, while recent multimodal large language models (LLMs) remain vulnerable to temporal inconsistency and unverified attributions. This paper introduces M-ArtAgent, an evidence-based multimodal agent that reframes implicit influence discovery as probabilistic adjudication. It follows a four-phase protocol consisting of Investigation, Corroboration, Falsification, and Verdict governed by a Reasoning and Acting (ReAct)-style controller that assembles verifiable evidence chains from images and biographies, enforces art-historical axioms, and subjects each hypothesis to adversarial falsification via…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
