While MLLMs can often identify what happens in a video, they still struggle with fine-grained spatio-temporal reasoning, which requires precise grounding when and where the supporting evidence appears and composing such evidence into a coherent reasoning chain. This challenge is exacerbated by the lack of scalable data construction and evaluation pipelines that provide granular, verifiable supervision linking reasoning steps to explicit spatio-temporal evidence.To address this gap, we present V-STORM, a structure-aware framework that transforms videos into Spatio-Temporal Scene Graphs (STSGs) and derives Grounded Chain of Thought (GCoT) from validated evidence paths, making each reasoning step traceable to structured and verifiable spatio-temporal evidence.Under this framework, we construct a 260K-sample training set and a 3K-sample human-verified benchmark, both featuring GCoT annotations that link reasoning to explicit spatio-temporal evidence.Experiments reveal a clear separation between evidence localization and evidence composition: current MLLMs can often identify relevant spatio-temporal cues, yet still fail to integrate them into correct multi-step reasoning, exposing a bottleneck that answer-only evaluation largely obscures. Moreover, fine-tuning with V-STORM substantially improves both answer accuracy and grounding faithfulness, validating its effectiveness as supervision for faithful and evidence-grounded video reasoning. Our dataset, benchmark, and source code will be publicly released.
Figures & tables
Figure 1: Overview of V-STORM. (a) Construction Pipeline: Unlike traditional methods, V-STORM employs a structure-aware framework with multi-model collaboration to generate complex tasks and verifiable CoT annotations. (b) Task Taxonomy: We design 11 tasks spanning Perception , Reasoning , and Combination dimensions. (c) Examples: Sample queries demonstrating fine-grained grounding (specific timestamps and coordinates) in both questions and GCoT. (d) Statistics: Dataset distribution highlighting the scale (260k), diversity, and high-quality verification.
Dataset
Training Set
Grounding
Compositional
Annotation
Construction
Video-Free
Scale
Spatial
Temporal
ST-Reasoning
CoT
Verifiable
Paradigm
Extension
Video-MME ( Fu et al. 2025 )
–
–
–
–
–
–
Human
–
MotionBench ( Hong et al. 2025 )
–
–
–
–
–
–
Human
–
NExT-QA ( Xiao et al. 2021 )
–
–
–
–
–
–
Human
–
ECBench ( Dang et al. 2025 )
–
–
–
–
–
–
Human
–
VCR-Bench ( Qi et al. 2025 )
–
✓
✓
–
GCoT
–
LLM+Human
–
Table 1: Comparison of representative video reasoning datasets. We compare existing datasets across scale, grounding, reasoning capability, and construction paradigm. Compositional ST-Reasoning denotes multi-hop spatio-temporal reasoning ability. GCoT uses language-based spatio-temporal reasoning traces, while MMCoT denotes interleaved multimodal CoT.
Figure 2: V-STORM Data Construction Pipeline. The pipeline consists of three stages: (i) Hybrid Perception & STSG Construction, (ii) Programmatic Question Generation, and (iii) Traceable Verification. The STSG serves as the core asset that connects raw video to generated structured samples.
Figure 3: Distribution of video lengths in the Training Split and Benchmark, and video topics in the Benchmark.
Question Category
Samples
Before
After
Imp. ( Δ )
Frame-Level Perception
100
82%
98%
+16%
Segment-Level Perception
100
78%
96%
+18%
Temporal Reasoning
100
71%
92%
+21%
Compositional Reasoning
100
64%
94%
+30%
Overall / Average
400
73.8%
95.0%
+21.2%
Table 2: Human audit results on the training split.
Model
FPS
Frame-Level
Segment-Level
Temporal Reasoning
Comp. Reasoning
Overall
Perception (Acc)
Perception (Acc)
Acc
R
G
Acc
R
G
Acc
R
G
Commercial Models
GPT-5.2
2
75.95
90.36
79.12
3.25
3.58
41.71
2.63
3.75
69.91
2.80
3.70
Qwen3.6-plus
2
73.42
91.30
80.93
3.43
3.97
40.36
2.75
3.96
69.38
2.93
3.97
Gemini3-Flash
1
69.71
87.81
75.52
3.02
3.61
34.84
2.51
4.06
64.97
2.65
3.94
Open-Source Models
Table 3: Performance of representative commercial and open-source multimodal models on the V-STORM Benchmark . Results are reported across four capability categories using accuracy (Acc) as the primary metric, with auxiliary Reasoning (R) and Grounding (G) scores for evidence-aligned spatio-temporal reasoning. Best scores are bold , and second-best are underlined .
Figure 4: Definition of Answer Accuracy, Reasoning Score, and Grounding Score.
Metric
FSG-Node
FSG-Edge
Segment STSG
Video STSG
Acc
92%
88%
91%
95%
Table 4: Human audit accuracy (Acc) across STSG construction stages: node category/bbox, edge relation, segment trajectory/event, and video-level identity/event integration.
Figure 5: Inference Prompt (Top) and Failure Cases on the V-STORM benchmark. Middle: the model recognizes the correct subject but selects a wrong region due to semantic granularity mismatching. Bottom: the model correctly grounds the object at first but fails to track it later.
Method
VideoRefer
NExT-QA
MMBench-V
EOC
Qwen3-VL-2B
67.20
74.88
1.3078
40.82
+ VSTORM
68.60
75.92
1.3163
42.32
Table 5: Performance on OOD benchmarks.
Strategy
FG
CG
General
Complex
Overall
baseline
60.25
86.77
73.91
22.11
58.08
sft w/o CoT (95k)
72.66
87.52
72.94
70.84
76.87
sft w/ CCoT (95k)
74.43
87.43
74.23
71.21
77.57
sft w/ GCoT (95k)
76.20
87.71
75.26
73.19
78.84
GCoT vs Non-CoT
+3.54
+0.19
+2.32
+2.35
+1.97
GCoT vs CCoT
+1.77
+0.28
+1.03
+1.98
+1.27
Table 6: Impact of different reasoning supervision strategies on various spatio-temporal tasks. (FG: Fine-grained Task, CG: Coarse-grained Task, CCoT: Coarse-grained CoT)