# Multimodal reasoning

Area: [LLM reasoning](https://mlsanity.com/lr/index.md). HTML: https://mlsanity.com/lr/multimodal-reasoning/

## Key facts

- Multimodal reasoning: 2,683 papers on arXiv since 2022 (data through 14 Oct 2026).
- 470 of its 2,683 mapped papers (18%) cite “MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts” (2023, arXiv 2310.02255).
- 300 of its 2,683 mapped papers (11%) cite “Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering” (2022, arXiv 2209.09513).
- 111 new papers 17 Sep–14 Oct.

## Most cited here

- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023), cited by 470 papers here
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022), cited by 300 papers here
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023), cited by 281 papers here
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022), cited by 279 papers here
- [Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset](https://mlsanity.com/paper/2402.14804/) (2024), cited by 277 papers here
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025), cited by 260 papers here
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024), cited by 236 papers here
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024), cited by 230 papers here
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023), cited by 214 papers here
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025), cited by 204 papers here

## New (17 Sep–14 Oct)

- [VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs](https://mlsanity.com/paper/2610.20083/) (2026-10-14)
- [Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching](https://mlsanity.com/paper/2610.19628/) (2026-10-14)
- [Frame Evidence:A Benchmark for Reference Frames and Visual Evidence in Multi-Image Spatial Reasoning](https://mlsanity.com/paper/2610.19564/) (2026-10-14)
- [Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs](https://mlsanity.com/paper/2610.18858/) (2026-10-13)
- [Rethinking Projector Training in Multimodal LLMs](https://mlsanity.com/paper/2610.18598/) (2026-10-13)
- [ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensing](https://mlsanity.com/paper/2610.18388/) (2026-10-13)
- [Benchmarking Multimodal Large Language Models for Zero-Shot Human-Object Interaction](https://mlsanity.com/paper/2610.18161/) (2026-10-13)
- [MERIT: Multimodal Evidence Reasoning over Image Tables](https://mlsanity.com/paper/2610.17937/) (2026-10-13)
- [The Image Still Has a Say: Final-Answer Repair for Multimodal Chain-of-Thought](https://mlsanity.com/paper/2610.17663/) (2026-10-13)
- [Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence](https://mlsanity.com/paper/2610.17656/) (2026-10-13)
- [Rethinking LLM-Guided Visual Question Answering: Does Deeper Knowledge Integration Really Help?](https://mlsanity.com/paper/2610.17079/) (2026-10-12)
- [Neos: Learning to Interleave Search and Visual Reasoning](https://mlsanity.com/paper/2610.17043/) (2026-10-12)
- [When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction](https://mlsanity.com/paper/2610.16615/) (2026-10-12)
- [Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning](https://mlsanity.com/paper/2610.15810/) (2026-10-11)
- [Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning](https://mlsanity.com/paper/2610.15565/) (2026-10-11)
- [VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning](https://mlsanity.com/paper/2610.14939/) (2026-10-10)
- [VisualCoding: Learning Executable Skills for Reliable Visual Reasoning](https://mlsanity.com/paper/2610.14403/) (2026-10-09)
- [Thinking with Images without Coordinates](https://mlsanity.com/paper/2610.14265/) (2026-10-09)
- [ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning](https://mlsanity.com/paper/2610.13316/) (2026-10-09)
- [OWLET: On-Policy Weighted Learning via Evidence Transfer for Video Large Language Model Post-Training](https://mlsanity.com/paper/2610.13272/) (2026-10-09)
- [MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph](https://mlsanity.com/paper/2610.12961/) (2026-10-09)
- [CaptchaAgent: Verifiable Visual Reasoning for CAPTCHA Solving](https://mlsanity.com/paper/2610.12866/) (2026-10-09)
- [OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning](https://mlsanity.com/paper/2610.12458/) (2026-10-08)
- [WOVEN: Weaving Visual World Modeling into Multimodal LLMs](https://mlsanity.com/paper/2610.12417/) (2026-10-08)
- [Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning](https://mlsanity.com/paper/2610.12060/) (2026-10-08)
- [Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder](https://mlsanity.com/paper/2610.11374/) (2026-10-08)
- [TerraAgent: Demonstration-Grounded Multi-Agent Reasoning for Long-Context Remote Sensing Visual Question Answering](https://mlsanity.com/paper/2610.12517/) (2026-10-07)
- [Less from More: Reinforcing Sparse Video Reasoning from Dense References](https://mlsanity.com/paper/2610.10893/) (2026-10-07)
- [SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages](https://mlsanity.com/paper/2610.10889/) (2026-10-07)
- [VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning](https://mlsanity.com/paper/2610.10782/) (2026-10-07)