TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917555656982528 |
|---|---|
| author | Ma, Xinkai Bai, Zhiqi Zhang, Dingling Liu, Pei Yuan, Yishuo Zhu, He Wang, Jiakai Xie, Qianqian Zhao, Yifan Yang, Xinlong Cong, Hao Yao, Zhiheng Xie, Fengxia Xu, Zihao Xu, Haoran Wang, Zhaohui Liu, Minghao Lin, Shirong Tan, Yingshui Xu, Yuchi Su, Wenbo Zhang, Zhaoxiang Zheng, Bo Liu, Jiaheng |
| author_facet | Ma, Xinkai Bai, Zhiqi Zhang, Dingling Liu, Pei Yuan, Yishuo Zhu, He Wang, Jiakai Xie, Qianqian Zhao, Yifan Yang, Xinlong Cong, Hao Yao, Zhiheng Xie, Fengxia Xu, Zihao Xu, Haoran Wang, Zhaohui Liu, Minghao Lin, Shirong Tan, Yingshui Xu, Yuchi Su, Wenbo Zhang, Zhaoxiang Zheng, Bo Liu, Jiaheng |
| contents | Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements are factually reliable and well aligned with the surrounding analysis. To address this gap, we introduce TVIR (Text--Visual Interleaved Report Generation), which includes TVIR-Bench, a benchmark of 100 expert-curated multimodal deep research tasks that require visual elements to serve specific analytical sub-goals, and TVIR-Agent, a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines, retrieving images, generating charts with traceable sources, and composing reports through context-aware sequential writing. We further develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment. Experiments across nine deep research systems show that TVIR-Agent achieves strong overall performance, underscoring the importance of explicit multimodal design and evaluation for evidence-driven report generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02320 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation Ma, Xinkai Bai, Zhiqi Zhang, Dingling Liu, Pei Yuan, Yishuo Zhu, He Wang, Jiakai Xie, Qianqian Zhao, Yifan Yang, Xinlong Cong, Hao Yao, Zhiheng Xie, Fengxia Xu, Zihao Xu, Haoran Wang, Zhaohui Liu, Minghao Lin, Shirong Tan, Yingshui Xu, Yuchi Su, Wenbo Zhang, Zhaoxiang Zheng, Bo Liu, Jiaheng Computation and Language Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements are factually reliable and well aligned with the surrounding analysis. To address this gap, we introduce TVIR (Text--Visual Interleaved Report Generation), which includes TVIR-Bench, a benchmark of 100 expert-curated multimodal deep research tasks that require visual elements to serve specific analytical sub-goals, and TVIR-Agent, a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines, retrieving images, generating charts with traceable sources, and composing reports through context-aware sequential writing. We further develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment. Experiments across nine deep research systems show that TVIR-Agent achieves strong overall performance, underscoring the importance of explicit multimodal design and evaluation for evidence-driven report generation. |
| title | TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2606.02320 |