| title | Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation |
|---|---|
| authors | Chenghao Zhang, Guanting Dong, Yufan Liu, Tong Zhao, Zhicheng Dou |
| date | 2026-05-28 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.29861 |
| affiliation | Renmin University of China |
| upvotes | 10 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without deterministic ground truth and the need to interleave textual arguments with visual evidence. We propose Ptah, a multi-agent harness for interleaved report generation. Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages, where specialized agents construct visual-aware plans, collect claim-grounded evidence, maintain source-aligned images in a Visual Working Memory, and compose reports through declarative multimodal tool use. A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow. We further introduce PtahEval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that Ptah produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines. |
cite
@misc{zhang2026towards,
title={Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation},
author={Chenghao Zhang and Guanting Dong and Yufan Liu and Tong Zhao and Zhicheng Dou},
year={2026},
eprint={2605.29861},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.29861}
}