mlsanityData to 14 Oct 2026

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

arXiv 2511.03845 ↗First posted 5 Nov 2025cs.AI cs.LGcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 2 more
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.

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.

Builds on

25 of 32 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models27 Mar
  2. 2025Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!18 Jan

Other references · 23

  1. 2024GPT-4o System Cardcited by 4,588
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  3. 2024A Survey on LLM-as-a-Judgecited by 1,423
  4. 2018Self-Attentive Sequential Recommendationcited by 1,184
  5. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  6. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  7. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 476
  8. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  9. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 242
  10. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
  11. 2023LLMRec: Large Language Models with Graph Augmentation for Recommendationcited by 172
  12. 2015Imaging Time-Series to Improve Classification and Imputationcited by 85
11 more
  1. 2021Global Context Enhanced Graph Neural Networks for Session-based Recommendationcited by 81
  2. 2024Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiencycited by 31
  3. 2025Towards Agentic Recommender Systems in the Era of Multimodal Large Language Modelscited by 26
  4. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systemscited by 23
  5. 2024LLMs for Relational Reasoning: How Far are We?cited by 21
  6. 2018DeepMove: Learning Place Representations through Large Scale Movement Datacited by 12
  7. 2019Time2Graph: Revisiting Time Series Modeling with Dynamic Shapeletscited by 12
  8. 2024Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendationscited by 9
  9. 2025GRACE: Generative Recommendation via Journey-Aware Sparse Attention on Chain-of-Thought Tokenizationcited by 4
  10. 2022Sequential Recommendation Model for Next Purchase Predictioncited by 3
  11. 2025Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classificationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications
  2. 2024Large Multimodal Agents: A Survey
  3. 2026Benchmarking LLM Tool-Use in the Wild
  4. 2026Vela: User Behavior as Supervision Sparks LLM Intelligence
  5. 2025Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs
  6. 2025VIVA+: Human-Centered Situational Decision-Making
  7. 2026Compliance, Capability, and Conflict: Benchmarking Multimodal LLMs under System Messages
  8. 2025DeepEyesV2: Toward Agentic Multimodal Model