# VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA

arXiv: https://arxiv.org/abs/2605.04870 · HTML: https://mlsanity.com/paper/2605.04870/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 6 May 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 32)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling](https://mlsanity.com/paper/2501.12386/) (2025)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [All in One: Exploring Unified Video-Language Pre-training](https://mlsanity.com/paper/2203.07303/) (2022)
- [OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles](https://mlsanity.com/paper/2503.17352/) (2025)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting](https://mlsanity.com/paper/2211.10772/) (2022)
- [FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting](https://mlsanity.com/paper/2509.24304/) (2025)
- [A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension](https://mlsanity.com/paper/2305.03347/) (2023)
- [Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation](https://mlsanity.com/paper/2401.17904/) (2024)
- [Reading Between the Lanes: Text VideoQA on the Road](https://mlsanity.com/paper/2307.03948/) (2023)
- [MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios](https://mlsanity.com/paper/2505.21333/) (2025)
- [AdsQA: Towards Advertisement Video Understanding](https://mlsanity.com/paper/2509.08621/) (2025)
- [GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching](https://mlsanity.com/paper/2401.07080/) (2024)
- [Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues](https://mlsanity.com/paper/2412.12502/) (2024)
- [GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking](https://mlsanity.com/paper/2505.22228/) (2025)

## Abstract (arXiv)

Video text-based visual question answering (Video TextVQA) aims to answer questions by reasoning over visual textual content appearing in videos. Despite the strong multimodal video understanding capabilities of recent Video-LLMs, their performance on existing Video TextVQA benchmarks remains limited. To better understand this gap, we conduct an upper-bound analysis through frame-wise question answering, counting a sample as correct if any frame yields the right answer, which significantly outperforms direct video-based inference and reveals a substantial performance gap. The results suggest that the primary bottleneck lies in the localization of key question-relevant evidence, rather than in reasoning capacity itself. Building on this insight, we propose a question-guided agent framework that explicitly anchors the relevant keyframes before answering. The approach operates effectively in a training-free setting and consistently surpasses direct video inference. With additional supervised fine-tuning (SFT) and reinforcement learning (RL), it achieves an average improvement of +12.12 in accuracy and +11.15 in ANLS across benchmarks, establishing new state-of-the-art results. Our study underscores the critical role of explicit keyframe anchoring for advancing Video TextVQA. The code will be publicly released.