mlsanityData to 7 Oct 2026

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

arXiv 2507.01006 ↗First posted 1 Jul 2025cs.CV cs.AI cs.LGcited by 439

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at https://z.ai/blog/glm-4.6v. Code, models and more information are released at https://github.com/zai-org/GLM-V.

Key facts. Cited by 439 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 52 of its 68 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

52 of 68 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models19 May
  2. 2024DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models29 Oct
  3. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?1 Jul
  4. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset22 Feb
  5. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul

Other references · 46

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  10. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  11. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  12. 2025Gemma 3 Technical Reportcited by 1,686
34 more
  1. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  2. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  3. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  4. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 893
  5. 2016A Diagram Is Worth A Dozen Imagescited by 793
  6. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  7. 2023CogAgent: A Visual Language Model for GUI Agentscited by 692
  8. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  9. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  10. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
  11. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  12. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 494
  13. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  14. 2024AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agentscited by 450
  15. 2024WebVoyager: Building an End-to-End Web Agent with Large Multimodal Modelscited by 424
  16. 2024LVBench: An Extreme Long Video Understanding Benchmarkcited by 402
  17. 2025Seed1.5-VL Technical Reportcited by 367
  18. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  19. 2023Demystifying CLIP Datacited by 265
  20. 2023Data Filtering Networkscited by 247
  21. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 240
  22. 2025Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videoscited by 225
  23. 2024CogVLM2: Visual Language Models for Image and Video Understandingcited by 214
  24. 2023Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Textcited by 208
  25. 2025Spurious Rewards: Rethinking Training Signals in RLVRcited by 199
  26. 2024MuirBench: A Comprehensive Benchmark for Robust Multi-image Understandingcited by 178
  27. 2022Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmarkcited by 114
  28. 2024Multimodal Autoregressive Pre-training of Large Vision Encoderscited by 108
  29. 2024OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Textcited by 58
  30. 2025ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Modelscited by 56
  31. 2024Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Modelscited by 52
  32. 2024MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokenscited by 47
  33. 2025Scalable Chain of Thoughts via Elastic Reasoningcited by 32
  34. 2024WebQuest: A Benchmark for Multimodal QA on Web Page Sequencescited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 97; 2026: 342.

439 papers.

Sort:

By area:

  1. 2025MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipecited by 174
  2. 2026Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Groundingcited by 132
  3. 2025The Art of Scaling Reinforcement Learning Compute for LLMscited by 91
  4. 2026Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillationcited by 71
  5. 2025ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Datacited by 58
  6. 2025LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Callingcited by 58
  7. 2025Baichuan-M2: Scaling Medical Capability with Large Verifier Systemcited by 55
  8. 2026Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perceptioncited by 47
  9. 2026Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understandingcited by 46
  10. 2026UI-Venus-1.5 Technical Reportcited by 39
  11. 2025VideoScore2: Think before You Score in Generative Video Evaluationcited by 37
  12. 2025Fara-7B: An Efficient Agentic Model for Computer Usecited by 34
38 more
  1. 2026RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillationcited by 33
  2. 2025We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoningcited by 32
  3. 2025Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedbackcited by 31
  4. 2025VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelscited by 31
  5. 2025PAI-Bench: A Comprehensive Benchmark For Physical AIcited by 30
  6. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Modelscited by 27
  7. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 27
  8. 2026Code2World: A GUI World Model via Renderable Code Generationcited by 26
  9. 2025Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Spacecited by 25
  10. 2025Streaming Video Instruction Tuningcited by 25
  11. 2026GLM-OCR Technical Reportcited by 24
  12. 2025ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesiscited by 22
  13. 2026Think3D: Thinking with Space for Spatial Reasoningcited by 22
  14. 2026GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agentscited by 22
  15. 2026Dolphin-v2: Universal Document Parsing via Scalable Anchor Promptingcited by 20
  16. 2025A Survey on Agentic Multimodal Large Language Modelscited by 19
  17. 2025UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texturecited by 19
  18. 2025Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understandingcited by 18
  19. 2026OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMscited by 18
  20. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 18
  21. 2025Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Modelscited by 17
  22. 2025SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sportscited by 17
  23. 2026MolmoWeb: Open Visual Web Agent and Open Data for the Open Webcited by 17
  24. 2026OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoningcited by 16
  25. 2025VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agentscited by 15
  26. 2025VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representationcited by 15
  27. 2025NVIDIA Nemotron Nano V2 VLcited by 15
  28. 2025Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Followingcited by 14
  29. 2026IGenBench: Benchmarking the Reliability of Text-to-Infographic Generationcited by 14
  30. 2026GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RLcited by 14
  31. 2026DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generationcited by 14
  32. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  33. 2025DECEPTICON: How Dark Patterns Manipulate Web Agentscited by 13
  34. 2026Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understandingcited by 13
  35. 2025EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOcited by 11
  36. 2025Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentationscited by 11
  37. 2025FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Modelcited by 11
  38. 2025M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmarkcited by 11

50 most cited of 439 All 439 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
  2. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
  3. 2025Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
  4. 2025Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs
  5. 2025Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning
  6. 2024Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
  7. 2026See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection
  8. 2025GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking