mlsanityData to 14 Oct 2026

Agentic Design Review System

arXiv 2508.10745 ↗First posted 14 Aug 2025cs.AI cs.CV cs.LGcited by 2

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Evaluating graphic designs involves assessing it from multiple facets like alignment, composition, aesthetics and color choices. Evaluating designs in a holistic way involves aggregating feedback from individual expert reviewers. Towards this, we propose an Agentic Design Review System (AgenticDRS), where multiple agents collaboratively analyze a design, orchestrated by a meta-agent. A novel in-context exemplar selection approach based on graph matching and a unique prompt expansion method plays central role towards making each agent design aware. Towards evaluating this framework, we propose DRS-BENCH benchmark. Thorough experimental evaluation against state-of-the-art baselines adapted to the problem setup, backed-up with critical ablation experiments brings out the efficacy of Agentic-DRS in evaluating graphic designs and generating actionable feedback. We hope that this work will attract attention to this pragmatic, yet under-explored research direction.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 104 of its 139 references that are in the map. First posted on arXiv 14 Aug 2025.

Builds on

104 of 139 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models18 Oct

Other references · 103

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  8. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  9. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  10. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  11. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  12. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
38 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  2. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  3. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  4. 2021Grounded Language-Image Pre-trainingcited by 1,156
  5. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  6. 2023Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Modelscited by 1,062
  7. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040
  8. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  9. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  10. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  11. 2024VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMscited by 771
  12. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  13. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
  14. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  15. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  16. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 625
  17. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  18. 2024LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Modelscited by 584
  19. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 563
  20. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 445
  21. 2023AppAgent: Multimodal Agents as Smartphone Userscited by 415
  22. 2023TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understandingcited by 406
  23. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 357
  24. 2021AudioCLIP: Extending CLIP to Image, Text and Audiocited by 339
  25. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  26. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelscited by 316
  27. 2023GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interestcited by 302
  28. 2023MIMIC-IT: Multi-Modal In-Context Instruction Tuningcited by 267
  29. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 265
  30. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 256
  31. 2022Egocentric Video-Language Pretrainingcited by 232
  32. 2024AnyGPT: Unified Multimodal LLM with Discrete Sequence Modelingcited by 217
  33. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Outputcited by 195
  34. 2022MERLOT Reserve: Neural Script Knowledge through Vision and Language and Soundcited by 184
  35. 2024VITA: Towards Open-Source Interactive Omni Multimodal LLMcited by 173
  36. 2023MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learningcited by 172
  37. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 165
  38. 2024OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Webcited by 157

50 most cited of 103 All 103 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applicationscited by 1
  2. 2026Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GraphicBench: A Planning Benchmark for Graphic Design with Language Agents
  2. 2026Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks
  3. 2025PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs
  4. 2026EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
  5. 2026AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
  6. 2024Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping
  7. 2025APD-Agents: A Large Language Model-Driven Multi-Agents Collaborative Framework for Automated Page Design
  8. 2025CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design