# MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks

arXiv: https://arxiv.org/abs/2604.23788 · HTML: https://mlsanity.com/paper/2604.23788/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 16 of 16)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector](https://mlsanity.com/paper/2408.15857/) (2024)
- [ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter](https://mlsanity.com/paper/2305.07490/) (2023)
- [ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities](https://mlsanity.com/paper/2502.13832/) (2025)
- [LLaVA-Docent: Instruction Tuning with Multimodal Large Language Model to Support Art Appreciation Education](https://mlsanity.com/paper/2402.06264/) (2024)
- [The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting](https://mlsanity.com/paper/2505.12837/) (2025)
- [Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding](https://mlsanity.com/paper/2402.09750/) (2024)
- [CognArtive: Large Language Models for Automating Art Analysis and Decoding Aesthetic Elements](https://mlsanity.com/paper/2502.04353/) (2025)
- [Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation](https://mlsanity.com/paper/2504.12805/) (2025)
- [Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion Symbols](https://mlsanity.com/paper/2511.22929/) (2025)

## Abstract (arXiv)

Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangement. We present MIRAGE, an evidence-centric framework designed to scaffold the exploration of these "micro-interactions" in multi-figure artworks. While such cues are essential for deep narrative appreciation, they are often distributed across complex scenes and difficult for viewers to systematically identify. Existing vision-language models (VLMs) frequently fail to provide reliable assistance, offering ungrounded interpretations that lack traceable visual evidence. MIRAGE addresses this by constructing a structured intermediate representation capturing identities, pose cues, and gaze hypotheses. However, the challenge extends beyond extracting these cues to coordinating them during interpretation. Without an explicit mechanism to organize and reconcile relational evidence, models often collapse multiple interaction hypotheses into a single unstable or weakly grounded narrative, even when low-level signals are available. This representation allows users to verify how high-level interpretations are anchored in low-level visual facts. By separating spatial grounding from narrative generation, MIRAGE enables users to inspect and reason about figure-to-figure relationships through a verifiable evidence layer. We evaluate MIRAGE against painting-only VLM baselines using a blind assessment protocol. Results show that MIRAGE significantly improves identity consistency, reduces relational hallucinations, and increases the coverage of subtle interactions. These findings suggest that structured grounding can serve as a critical interaction control layer, providing the necessary scaffolding for a more reliable, transparent, and human-led understanding of complex visual narratives.