Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs

• URL: http://arxiv.org/abs/2601.09430v1
• Date: Wed, 14 Jan 2026 12:24:47 GMT
• Title: Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
• Authors: Rui Zhu, Xin Shen, Shuchen Wu, Chenxi Miao, Xin Yu, Yang Li, Weikang Li, Deguo Xia, Jizhou Huang,
• Abstract summary: Video-MSR is the first benchmark designed to evaluate Multi-hop Spatial Reasoning in dynamic video scenarios.<n>Our benchmark comprises 3,052 high-quality video instances with 4,993 question-answer pairs, constructed via a scalable, visually-grounded pipeline.<n>Our results underscore the efficacy of multi-hop spatial instruction data and establish Video-MSR as a vital foundation for future research.
• Score: 21.346216484639225
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmarks primarily focus on single-step perception-to-judgment tasks, leaving scenarios requiring complex visual-spatial logical chains significantly underexplored. To bridge this gap, we introduce Video-MSR, the first benchmark specifically designed to evaluate Multi-hop Spatial Reasoning (MSR) in dynamic video scenarios. Video-MSR systematically probes MSR capabilities through four distinct tasks: Constrained Localization, Chain-based Reference Retrieval, Route Planning, and Counterfactual Physical Deduction. Our benchmark comprises 3,052 high-quality video instances with 4,993 question-answer pairs, constructed via a scalable, visually-grounded pipeline combining advanced model generation with rigorous human verification. Through a comprehensive evaluation of 20 state-of-the-art MLLMs, we uncover significant limitations, revealing that while models demonstrate proficiency in surface-level perception, they exhibit distinct performance drops in MSR tasks, frequently suffering from spatial disorientation and hallucination during multi-step deductions. To mitigate these shortcomings and empower models with stronger MSR capabilities, we further curate MSR-9K, a specialized instruction-tuning dataset, and fine-tune Qwen-VL, achieving a +7.82% absolute improvement on Video-MSR. Our results underscore the efficacy of multi-hop spatial instruction data and establish Video-MSR as a vital foundation for future research. The code and data will be available at https://github.com/ruiz-nju/Video-MSR.

Related papers

• MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs [61.70050081221131]
  MVU-Eval is the first comprehensive benchmark for evaluating Multi-Video Understanding for MLLMs.<n>Our MVU-Eval mainly assesses eight core competencies through 1,824 meticulously curated question-answer pairs spanning 4,959 videos.<n>These capabilities are rigorously aligned with real-world applications such as multi-sensor synthesis in autonomous systems and cross-angle sports analytics.
  arXiv  Detail & Related papers  (2025-11-10T16:02:33Z)
• Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond [116.65158801881984]
  We introduce post-training strategies aimed at enhancing the facial expression reasoning capabilities of MLLMs.<n>We develop a unified and interpretable FER foundation model termed UniFER-7B.
  arXiv  Detail & Related papers  (2025-11-01T03:53:00Z)
• Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph [29.737059125885057]
  Video-STR achieves state-the-art results on various benchmarks, outperforming the base model by 13% on ML-Bench.<n>Code, model, and data will be released.
  arXiv  Detail & Related papers  (2025-10-13T03:26:56Z)
• Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models [78.32948112203228]
  Video understanding represents the most challenging frontier in computer vision.<n>Recent emergence of Video-Large Multitemporal Models has demonstrated remarkable capabilities in video understanding tasks.<n>Survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities.
  arXiv  Detail & Related papers  (2025-10-06T17:10:44Z)
• CVBench: Evaluating Cross-Video Synergies for Complex Multimodal Understanding and Reasoning [11.478276629279526]
  We present CVBench, the first comprehensive benchmark designed to assess cross-video relational reasoning rigorously.<n>CVBench comprises 1,000 question-answer pairs spanning three tiers: cross-video object association, cross-video event association, and cross-video complex reasoning.<n>Built from five domain-diverse video clusters, the benchmark challenges models to synthesise information across dynamic visual contexts.
  arXiv  Detail & Related papers  (2025-08-27T03:29:35Z)
• MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks [67.31276358668424]
  We introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in response to a query and link them together to generate the most informative answer.<n> AVHaystacks is an audio-visual benchmark comprising 3100 annotated QA pairs designed to assess the capabilities of LMMs in multi-video retrieval and temporal grounding task.<n>We propose a model-agnostic, multi-agent framework to address this challenge, achieving up to 89% and 65% relative improvements over baseline methods on BLEU@4 and GPT evaluation scores in QA task on our proposed AVHaystack
  arXiv  Detail & Related papers  (2025-06-08T06:34:29Z)
• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
  We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T17:28:26Z)
• MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval [61.414236415351446]
  We propose MomentSeeker, a novel benchmark for long-video moment retrieval (LMVR)<n>MomentSeeker is created based on long and diverse videos, averaging over 1200 seconds in duration.<n>It covers a variety of real-world scenarios in three levels: global-level, event-level, object-level, covering common tasks like action recognition, object localization, and causal reasoning.
  arXiv  Detail & Related papers  (2025-02-18T05:50:23Z)
• VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection [61.54044967253421]
  We introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essential spatial details and temporal coherence. Our construction pipeline employs a semantic-aware method to reduce redundancy, followed by generating QA pairs using GPT-4o. We propose a Hybrid LVLMs Collaboration framework, featuring a Frame Selector and a two-stage instruction fine-tuned reasoning LVLM.
  arXiv  Detail & Related papers  (2024-11-22T08:33:36Z)
• Zero-Shot Action Recognition in Surveillance Videos [5.070026408553652]
  Current AI-based video surveillance systems rely on core computer vision models that require extensive finetuning.<n>VideoLLaMA2 represents a significant leap in zero-shot performance, with 20% boost over the baseline.<n>Self-ReS additionally increases zero-shot action recognition performance to 44.6%.
  arXiv  Detail & Related papers  (2024-10-28T15:13:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.