# To See or To Read: User Behavior Reasoning in Multimodal LLMs

arXiv: https://arxiv.org/abs/2511.03845 · HTML: https://mlsanity.com/paper/2511.03845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

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

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Imaging Time-Series to Improve Classification and Imputation](https://mlsanity.com/paper/1506.00327/) (2015)
- [Global Context Enhanced Graph Neural Networks for Session-based Recommendation](https://mlsanity.com/paper/2106.05081/) (2021)
- [Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency](https://mlsanity.com/paper/2407.09519/) (2024)
- [Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2503.16734/) (2025)
- [AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems](https://mlsanity.com/paper/2505.19623/) (2025)
- [LLMs for Relational Reasoning: How Far are We?](https://mlsanity.com/paper/2401.09042/) (2024)
- [Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!](https://mlsanity.com/paper/2501.10674/) (2025)
- [DeepMove: Learning Place Representations through Large Scale Movement Data](https://mlsanity.com/paper/1807.04241/) (2018)
- [Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets](https://mlsanity.com/paper/1911.04143/) (2019)
- [Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations](https://mlsanity.com/paper/2410.12228/) (2024)
- [Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models](https://mlsanity.com/paper/2503.21435/) (2025)
- [GRACE: Generative Recommendation via Journey-Aware Sparse Attention on Chain-of-Thought Tokenization](https://mlsanity.com/paper/2507.14758/) (2025)
- [Sequential Recommendation Model for Next Purchase Prediction](https://mlsanity.com/paper/2207.06225/) (2022)
- [Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification](https://mlsanity.com/paper/2501.08305/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) are reshaping how modern agentic systems reason over sequential user-behavior data. However, whether textual or image representations of user behavior data are more effective for maximizing MLLM performance remains underexplored. We present textttBehaviorLens, a systematic benchmarking framework for assessing modality trade-offs in user-behavior reasoning across six MLLMs by representing transaction data as (1) a text paragraph, (2) a scatter plot, and (3) a flowchart. Using a real-world purchase-sequence dataset, we find that when data is represented as images, MLLMs next-purchase prediction accuracy is improved by 87.5% compared with an equivalent textual representation without any additional computational cost.