Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.29861 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914614212558848 |
|---|---|
| author | Zhang, Chenghao Dong, Guanting Liu, Yufan Zhao, Tong Dou, Zhicheng |
| author_facet | Zhang, Chenghao Dong, Guanting Liu, Yufan Zhao, Tong Dou, Zhicheng |
| contents | 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 \textsc{Ptah}, a multi-agent harness for interleaved report generation. \textsc{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 \textit{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 \textsc{Ptah}Eval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that \textsc{Ptah} produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29861 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation Zhang, Chenghao Dong, Guanting Liu, Yufan Zhao, Tong Dou, Zhicheng Computation and Language Artificial Intelligence 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 \textsc{Ptah}, a multi-agent harness for interleaved report generation. \textsc{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 \textit{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 \textsc{Ptah}Eval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that \textsc{Ptah} produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines. |
| title | Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.29861 |