es, as reported in Table 1. EC-RAG yields consistent improvements for every backbone, with gains most pronounced on long videos where uniform sampling alone cannot cover the query-relevant content. The benefit is especially evident on frame-constrained backbones, confirming that event-chain retrieval compensates effectively for sparse visual input. The pipeline injects approximately 2 K tokens of supplementary textual context (the #Text column), comparable to roughly 14 extra keyframes in payload, which complement the visual input and help anchor temporal reasoning.
Scaling to the 72B LLaVA-Video, EC-RAG achieves 75.7% overall, surpassing both GPT-4o (OpenAI, 2024) and Gemini-1.5-Pro (Team et al., 2024), showing that structured event-chain retrieval enables open-source models to outperform proprietary systems without additional pretraining. EC-RAG also consistently outperforms Video-RAG (Luo et al., 2024) and TV-RAG (Cao et al., 2025) under the same backbone setting, as event-level temporal localization provides more precise context than frame-level retrieval.
Table 2. Overall accuracy on the multiple-choice split of the MLVU (Zhou et al., 2024) benchmark. EC-RAG achieves the best result among all 7B-scale models.
Model
#Params
Frames
Overall
Proprietary LVLMs
GPT-4o (OpenAI, 2024)
–
0.5 fps
64.6
Open-Source LVLMs
Video-CCAM (Fei et al., 2024)
14B
96
63.1
Video-XL (Shu et al., 2025)
7B
256
64.9
Aria (Li et al., 2024)
25.3B
256
70.6
LLaVA-Video (Zhang et al., 2024e)
7B
64
70.8
Oryx-1.5 (Liu et al., 2024b)
32B
128
72.3
LLaVA-Video + Video-RAG (Luo et al., 2024)
7B
64
72.4
LLaVA-Video + TV-RAG (Cao et al., 2025)
7B
64
72.6
LLaVA-Video + EC-RAG
7B
64
72.9
Figure 3. Left: Grad-CAM heatmaps on query-relevant and query-irrelevant frames for the baseline and EC-RAG. Right: t-SNE projection of query, vision, and text features, showing tighter cross-modal alignment when EC-RAG is applied.Grad-CAM attention heatmaps and t-SNE feature projections comparing baseline and EC-RAG cross-modal alignment.
MLVU.
Table 2 reports performance on the MLVU multiple-choice task.
EC-RAG lifts LLaVA-Video-7B from 70.8 to 72.9, outperforming both Video-RAG and TV-RAG on the same backbone.
Notably, this 7B model with only 64 frames also surpasses Oryx-1.5 (Liu et al., 2024b), a 32B model operating on 128 frames, highlighting the efficiency of event-chain retrieval over brute-force scaling.
LongVideoBench.
As shown in Table 3, EC-RAG also achieves the best result on LongVideoBench, reaching 59.5 with LLaVA-Video-7B at 64 frames.
This benchmark requires retrieving and composing evidence distributed across long timelines, a scenario that directly benefits from EC-RAG’s temporal event chain design.
Compared with Video-RAG and TV-RAG under the same setting, EC-RAG provides a more substantial boost over the unaugmented baseline, indicating that event-level localization is more effective than flat retrieval when evidence is temporally scattered.
Table 3. Performance on the LongVideoBench (Wu et al., 2024) validation set.
Model
#Params
Frames
Overall
VideoChat2-Mistral (Li et al., 2025)
7B
8
39.3
ShareGPT4Video (Chen et al., 2024b)
7B
8
39.7
LLaVA-Next-Mistral (Zhang et al., 2024d)
7B
8
49.1
PLLaVA (Xu et al., 2024)
34B
16
53.2
LLaVA-Video (Zhang et al., 2024e)
7B
64
56.6
LLaVA-Video + Video-RAG (Luo et al., 2024)
7B
64
58.7
LLaVA-Video + TV-RAG (Cao et al., 2025)
7B
64
58.8
LLaVA-Video + EC-RAG
7B
64
59.5
4.3. Ablation Studies
Figure 4. Qualitative comparison between the baseline LLaVA-Video and EC-RAG on a Video-MME example. The baseline confuses temporally distinct segments, whereas EC-RAG localizes the query-relevant event through its event chain and aggregates ASR and DET evidence to arrive at the correct answer.A qualitative case study showing how EC-RAG correctly answers a temporal reasoning question by localizing the relevant event and aggregating multimodal evidence.
To quantify each component’s contribution, we ablate EC-RAG on Video-MME with LLaVA-Video