Multimodal Reasoning
Overview
Multimodal reasoning studies how models perceive information across modalities, connect that evidence to knowledge, and use it to answer questions, plan actions, or explain decisions. Common approaches include instruction tuning and chain-of-thought training, reinforcement learning with verifiable rewards, tool-using agents, and structured methods such as graphs or symbolic solvers. Benchmarks such as MathVista and MMMU test visual problem solving, while video, document, scientific, and medical tasks probe reasoning across time and specialized evidence. A central challenge is ensuring that correct answers actually depend on relevant multimodal evidence rather than language shortcuts; grounding, cross-modal integration, and reliable generalization remain difficult.
Latest papers
531 papers29 papers in the last four weeks, down 44% on the four weeks before. 0.2% of all new papers.
PhysScope: Agentic Multimodal Physics Reasoning with Grounded Visual Memory
Synergizing Evidence Retrieval and Utilization for Self-Improving Multimodal Scientific Document Reasoning
PACD: Provenance-Aware Consensus Decoding for Mitigating Cross-Modal Hallucinations in Omnimodal Large Language Models
PURE: A Diagnostic Benchmark for Multi-Granularity Multimodal Identity Matching
Asymmetric Multimodal Learning with Decomposed JEPAs
A Unified Interpretable Semantic Framework for Multi-Modal Fiber Sensing Under Data Scarcity
A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents
Layer Roles Matter: Mitigating Modality Imbalance in Multimodal Emotion Reasoning via Adaptive Layer Profiling
DISCOVER: Online Variance-Guided Data Discovery for Budgeted Multimodal GRPO
EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning
Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning
Seeing vs. Counting: Complexity Twins Show Where Multimodal LLMs Fail on Diagrams
AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM Inference
Trick-or-Treat: Adversarial Evaluation of Multimodal Medical Reasoning with Synthetic Images
A Systematic Benchmark for Evaluating Multimodal Personalized Reasoning of Vision-Language Models
MPRBench, a novel and comprehensive benchmark specifically designed to evaluate personalized reasoning across a wide range of tasks and real-world challenges. MPRBench consists of 12 sub-tasks and additionally supports interpretable analysis of representative error cases. Through extensive experiments, we find that current personalized MLLMs still struggle with personalized reasoning due to several key challenges, including inaccurate recognition of personalized concepts and sensitivity to irrelevant personal information. We hope that MPRBench will stimulate further research on personalized reasoning in MLLMs. Code and data are available at https://github.com/kkdh15/MPRBench