# M-ArtAgent: Evidence-Based Multimodal Agent for Implicit Art Influence Discovery

arXiv: https://arxiv.org/abs/2604.07468 · HTML: https://mlsanity.com/paper/2604.07468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Benchmarking Vision Language Models for Cultural Understanding](https://mlsanity.com/paper/2407.10920/) (2024)
- [CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification](https://mlsanity.com/paper/2204.14244/) (2022)
- [The Shape of Art History in the Eyes of the Machine](https://mlsanity.com/paper/1801.07729/) (2018)
- [GalleryGPT: Analyzing Paintings with Large Multimodal Models](https://mlsanity.com/paper/2408.00491/) (2024)
- [Quantifying Creativity in Art Networks](https://mlsanity.com/paper/1506.00711/) (2015)
- [StyleBabel: Artistic Style Tagging and Captioning](https://mlsanity.com/paper/2203.05321/) (2022)
- [Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage](https://mlsanity.com/paper/2308.07151/) (2023)
- [A survey on knowledge-enhanced multimodal learning](https://mlsanity.com/paper/2211.12328/) (2022)
- [Toward Automated Discovery of Artistic Influence](https://mlsanity.com/paper/1408.3218/) (2014)
- [Multimodal Metadata Assignment for Cultural Heritage Artifacts](https://mlsanity.com/paper/2406.00423/) (2024)
- [Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations](https://mlsanity.com/paper/2504.00851/) (2025)
- [MoRA: LoRA Guided Multi-Modal Disease Diagnosis with Missing Modality](https://mlsanity.com/paper/2408.09064/) (2024)
- [Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning](https://mlsanity.com/paper/2409.01035/) (2024)
- [Towards Cross-modal Retrieval in Chinese Cultural Heritage Documents: Dataset and Solution](https://mlsanity.com/paper/2505.10921/) (2025)
- [WP-CLIP: Leveraging CLIP to Predict W"olfflin's Principles in Visual Art](https://mlsanity.com/paper/2508.12668/) (2025)

## Abstract (arXiv)

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 a prompt-isolated critic. Two theory-grounded operators, StyleComparator for Wolfflin formal analysis and ConceptRetriever for ICONCLASS-based iconographic grounding, ensure that intermediate claims are formally auditable. On the balanced WikiArt Influence Benchmark-100 (WIB-100) of 100 artists and 2,000 directed pairs, M-ArtAgent achieves 83.7% positive-class F1, 0.666 Matthews correlation coefficient (MCC), and 0.910 area under the receiver operating characteristic curve (ROC-AUC), with leakage-control and robustness checks confirming that the gains persist when explicit influence phrases are masked. By coupling multimodal perception with domain-constrained falsification, M-ArtAgent demonstrates that implicit influence analysis benefits from historically grounded adjudication rather than pattern matching alone.